Files
explore-tis-untrunc-45-8B/training_logs/explore-tis-untrunc_736687.out
ModelHub XC e73842f34f 初始化项目,由ModelHub XC社区提供模型
Model: laion/explore-tis-untrunc-45-8B
Source: Original Platform
2026-08-08 15:29:19 +08:00

7560 lines
835 KiB
Plaintext
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

The following have been reloaded with a version change:
1) GCCcore/.14.3.0 => GCCcore/14.3.0
Lmod is automatically replacing "GCC/14.3.0" with
"nvidia-compilers/25.9-CUDA-13".
Deactivating conda environment: /e/scratch/jureap59/feuer1/miniforge3/envs/otagent
Activating RL environment: /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl
Python executable: /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/bin/python
Python path check: /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/bin/python
[ray] RAY_TMPDIR=/tmp/ray/ray_736687
[triton_cache] Triton cache: /tmp/triton_cache_feuer1_736687
[triton_cache] TorchInductor cache: /tmp/torchinductor_cache_feuer1_736687
[proxy] ✓ Found proxychains binary at /e/scratch/jureap59/feuer1/proxychains-ng-aarch64/bin/proxychains4
[proxy] Setting up SSH tunnel to jpbl-s01-01
[proxy] SSH key: /e/home/jusers/feuer1/jupiter/.ssh/authorized_keys/id_ed25519_jsc
[proxy] Tunnel port: 7003
[proxy] Node IP: 10.128.25.17 (workers will connect here)
[proxy] ✓ SSH tunnel started successfully
[proxy] ✓ Generated proxychains config at /e/home/jusers/feuer1/jupiter/.proxychains/proxychains_736687.conf
[proxy] - Internal traffic (10.x.x.x, 172.x.x.x, 169.254.x.x) → DIRECT
[proxy] - External traffic (internet) → PROXY via tunnel
[proxy] ✓ Daytona timeout settings configured
[proxy] Testing proxy connectivity...
[proxychains] config file found: /e/home/jusers/feuer1/jupiter/.proxychains/proxychains_736687.conf
[proxychains] preloading /e/scratch/jureap59/feuer1/proxychains-ng-aarch64/lib/libproxychains4.so
[proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e
[proxy] ✓ Proxy connectivity test passed (huggingface.co reachable via wrapped binary)
[proxy] ✓ Tunnel accessible at 10.128.25.17:7003 (workers can connect)
[proxy] ✓ Proxy setup complete (using wrapped binary for Ray workers)
[container_runtime] Using cloud backend: daytona (no local container setup)
=== Universal RL Training Runner ===
Config: /e/data1/datasets/playground/ot-baf/explore-tis-untrunc/configs/explore-tis-untrunc_rl_config.json
Working directory: /e/scratch/jureap59/feuer1/OpenThoughts-Agent
Python: /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/bin/python
Python version: Python 3.12.12
UV_USE_IO_URING: 0
Proxy: DISABLED (direct internet or not configured)
========================================
=== RLJobRunner: explore-tis-untrunc ===
[wandb_utils] Fixing permissions on: /e/data1/datasets/playground/ot-baf/explore-tis-untrunc/wandb
[wandb_utils] WandB directory ready: /e/data1/datasets/playground/ot-baf/explore-tis-untrunc/wandb
HF_TOKEN=****pDbg
HF_HUB_CACHE=/e/data1/datasets/playground/ot-baf/hf_hub
SUPABASE_URL=https://rpzmyuapoqilpghynmza.s... (direct Supabase config)
Environment configured:
TENSOR_PARALLEL_SIZE=1
NUM_INFERENCE_ENGINES=56
POLICY_NUM_NODES=14
WANDB_DIR=/e/data1/datasets/playground/ot-baf/explore-tis-untrunc/wandb
Starting Ray cluster with 14 nodes, 4 GPUs/node
Cleaning up existing Ray instances...
=== Starting Ray Cluster ===
Nodes: 14
GPUs per node: 4
CPUs per node: 288
Head node: jpbo-026-33 (10.128.25.17)
Ray port: 6379
============================
Starting Ray head on jpbo-026-33 (logging to /e/data1/datasets/playground/ot-baf/experiments/_ray_logs/ray_head_jpbo-026-33.log)...
Command: srun --export=ALL,VLLM_HOST_IP=10.128.25.17 --nodes=1 --ntasks=1 --gres=gpu:4 --gpu-bind=none --overlap --cpu-bind=none -w jpbo-026-33 bash -c /e/scratch/jureap59/feuer1/proxychains-ng-aarch64/bin/proxychains4 -f "$PROXYCHAINS_CONF_FILE" ray start --head --node-ip-address=10.128.25.17 --port=6379 --num-gpus=4 --num-cpus=288 --block --object-store-memory=42949672960
Started Ray head on jpbo-026-33
Starting Ray worker on jpbo-026-39 (logging to /e/data1/datasets/playground/ot-baf/experiments/_ray_logs/ray_worker_jpbo-026-39.log)...
Command: srun --export=ALL,VLLM_HOST_IP=10.128.25.23 --nodes=1 --ntasks=1 --gres=gpu:4 --gpu-bind=none --overlap --cpu-bind=none -w jpbo-026-39 bash -c /e/scratch/jureap59/feuer1/proxychains-ng-aarch64/bin/proxychains4 -f "$PROXYCHAINS_CONF_FILE" ray start --address=10.128.25.17:6379 --node-ip-address=10.128.25.23 --num-gpus=4 --num-cpus=288 --block --object-store-memory=42949672960
Started Ray worker 1 on jpbo-026-39
Starting Ray worker on jpbo-026-40 (logging to /e/data1/datasets/playground/ot-baf/experiments/_ray_logs/ray_worker_jpbo-026-40.log)...
Command: srun --export=ALL,VLLM_HOST_IP=10.128.25.24 --nodes=1 --ntasks=1 --gres=gpu:4 --gpu-bind=none --overlap --cpu-bind=none -w jpbo-026-40 bash -c /e/scratch/jureap59/feuer1/proxychains-ng-aarch64/bin/proxychains4 -f "$PROXYCHAINS_CONF_FILE" ray start --address=10.128.25.17:6379 --node-ip-address=10.128.25.24 --num-gpus=4 --num-cpus=288 --block --object-store-memory=42949672960
Started Ray worker 2 on jpbo-026-40
Starting Ray worker on jpbo-026-41 (logging to /e/data1/datasets/playground/ot-baf/experiments/_ray_logs/ray_worker_jpbo-026-41.log)...
Command: srun --export=ALL,VLLM_HOST_IP=10.128.25.25 --nodes=1 --ntasks=1 --gres=gpu:4 --gpu-bind=none --overlap --cpu-bind=none -w jpbo-026-41 bash -c /e/scratch/jureap59/feuer1/proxychains-ng-aarch64/bin/proxychains4 -f "$PROXYCHAINS_CONF_FILE" ray start --address=10.128.25.17:6379 --node-ip-address=10.128.25.25 --num-gpus=4 --num-cpus=288 --block --object-store-memory=42949672960
Started Ray worker 3 on jpbo-026-41
Starting Ray worker on jpbo-026-43 (logging to /e/data1/datasets/playground/ot-baf/experiments/_ray_logs/ray_worker_jpbo-026-43.log)...
Command: srun --export=ALL,VLLM_HOST_IP=10.128.25.27 --nodes=1 --ntasks=1 --gres=gpu:4 --gpu-bind=none --overlap --cpu-bind=none -w jpbo-026-43 bash -c /e/scratch/jureap59/feuer1/proxychains-ng-aarch64/bin/proxychains4 -f "$PROXYCHAINS_CONF_FILE" ray start --address=10.128.25.17:6379 --node-ip-address=10.128.25.27 --num-gpus=4 --num-cpus=288 --block --object-store-memory=42949672960
Started Ray worker 4 on jpbo-026-43
Starting Ray worker on jpbo-026-44 (logging to /e/data1/datasets/playground/ot-baf/experiments/_ray_logs/ray_worker_jpbo-026-44.log)...
Command: srun --export=ALL,VLLM_HOST_IP=10.128.25.28 --nodes=1 --ntasks=1 --gres=gpu:4 --gpu-bind=none --overlap --cpu-bind=none -w jpbo-026-44 bash -c /e/scratch/jureap59/feuer1/proxychains-ng-aarch64/bin/proxychains4 -f "$PROXYCHAINS_CONF_FILE" ray start --address=10.128.25.17:6379 --node-ip-address=10.128.25.28 --num-gpus=4 --num-cpus=288 --block --object-store-memory=42949672960
Started Ray worker 5 on jpbo-026-44
Starting Ray worker on jpbo-029-33 (logging to /e/data1/datasets/playground/ot-baf/experiments/_ray_logs/ray_worker_jpbo-029-33.log)...
Command: srun --export=ALL,VLLM_HOST_IP=10.128.25.161 --nodes=1 --ntasks=1 --gres=gpu:4 --gpu-bind=none --overlap --cpu-bind=none -w jpbo-029-33 bash -c /e/scratch/jureap59/feuer1/proxychains-ng-aarch64/bin/proxychains4 -f "$PROXYCHAINS_CONF_FILE" ray start --address=10.128.25.17:6379 --node-ip-address=10.128.25.161 --num-gpus=4 --num-cpus=288 --block --object-store-memory=42949672960
Started Ray worker 6 on jpbo-029-33
Starting Ray worker on jpbo-029-34 (logging to /e/data1/datasets/playground/ot-baf/experiments/_ray_logs/ray_worker_jpbo-029-34.log)...
Command: srun --export=ALL,VLLM_HOST_IP=10.128.25.162 --nodes=1 --ntasks=1 --gres=gpu:4 --gpu-bind=none --overlap --cpu-bind=none -w jpbo-029-34 bash -c /e/scratch/jureap59/feuer1/proxychains-ng-aarch64/bin/proxychains4 -f "$PROXYCHAINS_CONF_FILE" ray start --address=10.128.25.17:6379 --node-ip-address=10.128.25.162 --num-gpus=4 --num-cpus=288 --block --object-store-memory=42949672960
Started Ray worker 7 on jpbo-029-34
Starting Ray worker on jpbo-029-35 (logging to /e/data1/datasets/playground/ot-baf/experiments/_ray_logs/ray_worker_jpbo-029-35.log)...
Command: srun --export=ALL,VLLM_HOST_IP=10.128.25.163 --nodes=1 --ntasks=1 --gres=gpu:4 --gpu-bind=none --overlap --cpu-bind=none -w jpbo-029-35 bash -c /e/scratch/jureap59/feuer1/proxychains-ng-aarch64/bin/proxychains4 -f "$PROXYCHAINS_CONF_FILE" ray start --address=10.128.25.17:6379 --node-ip-address=10.128.25.163 --num-gpus=4 --num-cpus=288 --block --object-store-memory=42949672960
Started Ray worker 8 on jpbo-029-35
Starting Ray worker on jpbo-029-36 (logging to /e/data1/datasets/playground/ot-baf/experiments/_ray_logs/ray_worker_jpbo-029-36.log)...
Command: srun --export=ALL,VLLM_HOST_IP=10.128.25.164 --nodes=1 --ntasks=1 --gres=gpu:4 --gpu-bind=none --overlap --cpu-bind=none -w jpbo-029-36 bash -c /e/scratch/jureap59/feuer1/proxychains-ng-aarch64/bin/proxychains4 -f "$PROXYCHAINS_CONF_FILE" ray start --address=10.128.25.17:6379 --node-ip-address=10.128.25.164 --num-gpus=4 --num-cpus=288 --block --object-store-memory=42949672960
Started Ray worker 9 on jpbo-029-36
Starting Ray worker on jpbo-029-37 (logging to /e/data1/datasets/playground/ot-baf/experiments/_ray_logs/ray_worker_jpbo-029-37.log)...
Command: srun --export=ALL,VLLM_HOST_IP=10.128.25.165 --nodes=1 --ntasks=1 --gres=gpu:4 --gpu-bind=none --overlap --cpu-bind=none -w jpbo-029-37 bash -c /e/scratch/jureap59/feuer1/proxychains-ng-aarch64/bin/proxychains4 -f "$PROXYCHAINS_CONF_FILE" ray start --address=10.128.25.17:6379 --node-ip-address=10.128.25.165 --num-gpus=4 --num-cpus=288 --block --object-store-memory=42949672960
Started Ray worker 10 on jpbo-029-37
Starting Ray worker on jpbo-029-44 (logging to /e/data1/datasets/playground/ot-baf/experiments/_ray_logs/ray_worker_jpbo-029-44.log)...
Command: srun --export=ALL,VLLM_HOST_IP=10.128.25.172 --nodes=1 --ntasks=1 --gres=gpu:4 --gpu-bind=none --overlap --cpu-bind=none -w jpbo-029-44 bash -c /e/scratch/jureap59/feuer1/proxychains-ng-aarch64/bin/proxychains4 -f "$PROXYCHAINS_CONF_FILE" ray start --address=10.128.25.17:6379 --node-ip-address=10.128.25.172 --num-gpus=4 --num-cpus=288 --block --object-store-memory=42949672960
Started Ray worker 11 on jpbo-029-44
Starting Ray worker on jpbo-029-46 (logging to /e/data1/datasets/playground/ot-baf/experiments/_ray_logs/ray_worker_jpbo-029-46.log)...
Command: srun --export=ALL,VLLM_HOST_IP=10.128.25.174 --nodes=1 --ntasks=1 --gres=gpu:4 --gpu-bind=none --overlap --cpu-bind=none -w jpbo-029-46 bash -c /e/scratch/jureap59/feuer1/proxychains-ng-aarch64/bin/proxychains4 -f "$PROXYCHAINS_CONF_FILE" ray start --address=10.128.25.17:6379 --node-ip-address=10.128.25.174 --num-gpus=4 --num-cpus=288 --block --object-store-memory=42949672960
Started Ray worker 12 on jpbo-029-46
Starting Ray worker on jpbo-029-48 (logging to /e/data1/datasets/playground/ot-baf/experiments/_ray_logs/ray_worker_jpbo-029-48.log)...
Command: srun --export=ALL,VLLM_HOST_IP=10.128.25.176 --nodes=1 --ntasks=1 --gres=gpu:4 --gpu-bind=none --overlap --cpu-bind=none -w jpbo-029-48 bash -c /e/scratch/jureap59/feuer1/proxychains-ng-aarch64/bin/proxychains4 -f "$PROXYCHAINS_CONF_FILE" ray start --address=10.128.25.17:6379 --node-ip-address=10.128.25.176 --num-gpus=4 --num-cpus=288 --block --object-store-memory=42949672960
Started Ray worker 13 on jpbo-029-48
Waiting for cluster (56 GPUs, 14 nodes)...
Connecting to Ray at 10.128.25.17:6379 (expecting 14 nodes, 56.0 GPUs)
Ray connection established, polling for resources...
[Ray wait] nodes=14/14 GPUs=56.0/56.0 resources={'CPU': 4032.0, 'object_store_memory': 601295421440.0, 'memory': 10860264161280.0, 'GPU': 56.0, 'accelerator_type:GH200': 14.0, 'node:10.128.25.161': 1.0, 'node:10.128.25.176': 1.0, 'node:10.128.25.162': 1.0, 'node:10.128.25.25': 1.0, 'node:__internal_head__': 1.0, 'node:10.128.25.17': 1.0, 'node:10.128.25.23': 1.0, 'node:10.128.25.164': 1.0, 'node:10.128.25.165': 1.0, 'node:10.128.25.24': 1.0, 'node:10.128.25.172': 1.0, 'node:10.128.25.174': 1.0, 'node:10.128.25.28': 1.0, 'node:10.128.25.163': 1.0, 'node:10.128.25.27': 1.0}
✓ Ray cluster ready
=== Ray Cluster Ready ===
Address: 10.128.25.17:6379
Total GPUs: 56
=========================
Ray cluster ready at 10.128.25.17:6379
Total GPUs available: 56
[RLJobRunner] Pinggy check: url=False, token=False, needs_tunnel=False (agent=terminus-2, env=daytona)
[RLJobRunner] No Pinggy tunnel needed, using local vLLM
Running SkyRL:
Python: /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/bin/python
Entrypoint: examples.terminal_bench.entrypoints.main_tbench
Args: 126 Hydra arguments
Working dir: /e/scratch/jureap59/feuer1/OpenThoughts-Agent/SkyRL/skyrl-train
Using proxychains binary: /e/scratch/jureap59/feuer1/proxychains-ng-aarch64/bin/proxychains4
Executing command with srun: /e/scratch/jureap59/feuer1/proxychains-ng-aarch64/bin/proxychains4 -f $PROXYCHAINS_CONF_FILE /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/bin/python -m examples.terminal_bench.entrypoints.main_tbench +terminal_bench_config=terminal_bench trainer.strategy=fsdp2 trainer.algorithm.advantage_estimator=rloo_n trainer.algorithm.use_kl_loss=false trainer.algorithm.kl_loss_coef=0.0 trainer.algorithm.eps_clip_low=0.2 trainer.algorithm.eps_clip_high=0.05 trainer.algorithm.loss_reduction=seq_mean_token_sum_norm_global trainer.algorithm.use_tis=true trainer.algorithm.tis_imp_ratio_cap=2.0 trainer.epochs=2 trainer.max_steps=80 trainer.update_epochs_per_batch=1 trainer.train_batch_size=64 trainer.policy_mini_batch_size=64 trainer.eval_batch_size=64 trainer.micro_forward_batch_size_per_gpu=4 trainer.micro_train_batch_size_per_gpu=1 trainer.max_prompt_length=999999 trainer.eval_interval=999999 trainer.eval_before_train=false trainer.ckpt_interval=2 trainer.resume_mode=latest trainer.hf_save_interval=5 ++trainer.hf_hub_repo_id=laion/explore-tis-untrunc ++trainer.hf_hub_private=false ++trainer.hf_hub_revision=main ++trainer.enable_db_registration=false trainer.project_name=OpenThoughts-Agent trainer.log_level=INFO trainer.tracker_commit_each_step=true trainer.logger=console trainer.run_name=explore-tis-untrunc trainer.ckpt_path=/e/data1/datasets/playground/ot-baf/explore-tis-untrunc/explore-tis-untrunc/checkpoints trainer.export_path=/e/data1/datasets/playground/ot-baf/explore-tis-untrunc/explore-tis-untrunc/exports trainer.policy.optimizer_config.lr=8e-6 trainer.policy.optimizer_config.weight_decay=0.0 trainer.policy.optimizer_config.adam_betas=[0.9,0.999] trainer.policy.optimizer_config.max_grad_norm=0.9 trainer.policy.fsdp_config.cpu_offload=false trainer.policy.fsdp_config.reshard_after_forward=true trainer.policy.fsdp_config.fsdp_size=4 trainer.policy.model.path=/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6 trainer.ref.fsdp_config.cpu_offload=false trainer.ref.fsdp_config.reshard_after_forward=true trainer.ref.fsdp_config.fsdp_size=4 trainer.placement.colocate_all=false trainer.placement.policy_num_nodes=2 trainer.placement.ref_num_nodes=2 trainer.placement.policy_num_gpus_per_node=4 trainer.placement.ref_num_gpus_per_node=4 trainer.fully_async.max_staleness_steps=16 trainer.fully_async.num_parallel_generation_workers=338 generator.backend=vllm generator.timeout_multiplier=1.0 generator.model_dtype=bfloat16 generator.inference_engine_tensor_parallel_size=1 generator.num_inference_engines=48 generator.n_samples_per_prompt=8 generator.eval_n_samples_per_prompt=8 generator.gpu_memory_utilization=0.75 generator.max_num_seqs=24 generator.max_num_batched_tokens=65536 generator.enable_prefix_caching=true generator.enable_chunked_prefill=true generator.run_engines_locally=true generator.weight_sync_backend=nccl generator.async_engine=true generator.batched=false generator.enable_http_endpoint=true generator.enable_ray_prometheus_stats=false generator.vllm_stats_interval=1 generator.append_eos_token_after_stop_str_in_multi_turn=true generator.max_turns=999999 generator.sampling_params.max_generate_length=4096 generator.sampling_params.temperature=0.7 generator.sampling_params.top_p=0.95 generator.sampling_params.top_k=20 ++generator.engine_init_kwargs.max_model_len=32768 ++generator.engine_init_kwargs.custom_chat_template_chat_completion_path=chat_templates/qwen3_thinking_acc.jinja2 ++generator.engine_init_kwargs.served_model_name=0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6 data.train_data=["/e/scratch/jureap59/feuer1/tasks/exp_rpt_pymethods2test-large"] data.val_data=[] +terminal_bench_config.trials_dir=/e/data1/datasets/playground/ot-baf/explore-tis-untrunc/explore-tis-untrunc/trace_jobs +terminal_bench_config.harbor.name=terminus-2 +terminal_bench_config.harbor.max_episodes=999999 +terminal_bench_config.harbor.enable_summarize=false +terminal_bench_config.harbor.store_all_messages=true +terminal_bench_config.harbor.trajectory_config.raw_content=true +terminal_bench_config.harbor.enable_episode_logging=false +terminal_bench_config.harbor.record_terminal_session=false +terminal_bench_config.harbor.enable_pane_logging=false +terminal_bench_config.harbor.strict_json_parser=true +terminal_bench_config.harbor.interleaved_thinking=true +terminal_bench_config.harbor.extra_body.chat_template_kwargs.enable_thinking=true +terminal_bench_config.harbor.override_timeout_sec=900 +terminal_bench_config.harbor.override_cpus=1 +terminal_bench_config.harbor.override_memory_mb=2048 +terminal_bench_config.harbor.override_storage_mb=2048 +terminal_bench_config.harbor.auto_snapshot=true +terminal_bench_config.harbor.verifier_override_timeout_sec=120 +terminal_bench_config.harbor.max_retries=3 +terminal_bench_config.harbor.min_wait_sec=60.0 +terminal_bench_config.harbor.max_wait_sec=600.0 +terminal_bench_config.harbor.wait_multiplier=2.0 +terminal_bench_config.harbor.exclude_exceptions=["VerifierTimeoutError","VerifierRuntimeError","RewardFileNotFoundError","RewardFileEmptyError","VerifierOutputParseError"] +terminal_bench_config.harbor.n_concurrent_trials=675 +terminal_bench_config.harbor.log_level=INFO +terminal_bench_config.harbor.enable_reward_shaping=false +terminal_bench_config.harbor.collect_rollout_details=true +terminal_bench_config.harbor.enable_error_classification=true +terminal_bench_config.harbor.mask_exceptions=["DaytonaError","EnvironmentStartTimeoutError","NetworkError","ConnectionError","RewardFileNotFoundError","RewardFileEmptyError","AgentEnvironmentTimeoutError","ContextLengthExceededError"] +terminal_bench_config.harbor.default_error_treatment=zero +terminal_bench_config.harbor.passthrough_exceptions=["AgentTimeoutError"] +terminal_bench_config.harbor.zero_exceptions=[] +terminal_bench_config.model_info.max_input_tokens=32000 +terminal_bench_config.model_info.max_output_tokens=4096 +terminal_bench_config.archiving.enabled=false +terminal_bench_config.trace_upload.enabled=true +terminal_bench_config.trace_upload.repo_org=DCAgent +terminal_bench_config.trace_upload.episodes=last +terminal_bench_config.trace_upload.dataset_type=SFT +terminal_bench_config.trace_upload.cleanup=true generator.sampling_params.temperature=1.0 generator.sampling_params.top_p=1.0 generator.sampling_params.top_k=-1
[proxychains] config file found: /e/home/jusers/feuer1/jupiter/.proxychains/proxychains_736687.conf
[proxychains] preloading /e/scratch/jureap59/feuer1/proxychains-ng-aarch64/lib/libproxychains4.so
[proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e
2026-06-12 00:53:52.012 | WARNING | skyrl_train.utils.utils:validate_cfg:479 - `generator.sampling_params.logprobs` is `None` but `trainer.algorithm.use_tis` is `True`. Setting `logprobs` to `True`.
2026-06-12 00:53:52.180 | INFO | skyrl_train.utils.utils:prepare_runtime_environment:833 - Exporting wandb api key to ray runtime env
2026-06-12 00:53:52.180 | INFO | skyrl_train.utils.utils:prepare_runtime_environment:852 - Exporting RAY_ADDRESS to ray runtime env
2026-06-12 00:53:52.180 | INFO | skyrl_train.utils.utils:prepare_runtime_environment:877 - Exporting `NCCL_SOCKET_IFNAME` to ray runtime env: ib0
2026-06-12 00:53:52.180 | INFO | skyrl_train.utils.utils:prepare_runtime_environment:877 - Exporting `NCCL_SOCKET_FAMILY` to ray runtime env: AF_INET
2026-06-12 00:53:52.180 | INFO | skyrl_train.utils.utils:prepare_runtime_environment:877 - Exporting `NCCL_DEBUG` to ray runtime env: WARN
2026-06-12 00:53:52,180 INFO worker.py:1680 -- Using address 10.128.25.17:6379 set in the environment variable RAY_ADDRESS
2026-06-12 00:53:52,214 INFO worker.py:1821 -- Connecting to existing Ray cluster at address: 10.128.25.17:6379...
2026-06-12 00:53:52,222 WARNING node.py:1846 -- The object spilling config is specified from an unstable API - system config or environment variable. This is subject to change in the future. You can use the stable API - --object-spilling-directory in ray start or object_spilling_directory in ray.init() to specify the object spilling directory instead. If you need more advanced settings, please open a github issue with the Ray team.
2026-06-12 00:53:52,225 INFO worker.py:2007 -- Connected to Ray cluster.
/e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/ray/_private/worker.py:2046: FutureWarning: Tip: In future versions of Ray, Ray will no longer override accelerator visible devices env var if num_gpus=0 or num_gpus=None (default). To enable this behavior and turn off this error message, set RAY_ACCEL_ENV_VAR_OVERRIDE_ON_ZERO=0
warnings.warn(
(raylet) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e
(pid=348050) [2026-06-12 00:53:52,634 E 348050 349258] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14
(raylet) 2026-06-12 00:53:53,525 WARNING node.py:1846 -- The object spilling config is specified from an unstable API - system config or environment variable. This is subject to change in the future. You can use the stable API - --object-spilling-directory in ray start or object_spilling_directory in ray.init() to specify the object spilling directory instead. If you need more advanced settings, please open a github issue with the Ray team.
2026-06-12 00:53:54.651 | INFO | skyrl_train.utils.ppo_utils:sync_registries:546 - Synced registries to ray actor
(raylet) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 17x across cluster] (Ray deduplicates logs by default. Set RAY_DEDUP_LOGS=0 to disable log deduplication, or see https://docs.ray.io/en/master/ray-observability/user-guides/configure-logging.html#log-deduplication for more options.)
(pid=348068) [2026-06-12 00:53:58,380 E 348068 349758] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14 [repeated 8x across cluster]
(raylet) 2026-06-12 00:53:55,365 WARNING node.py:1846 -- The object spilling config is specified from an unstable API - system config or environment variable. This is subject to change in the future. You can use the stable API - --object-spilling-directory in ray start or object_spilling_directory in ray.init() to specify the object spilling directory instead. If you need more advanced settings, please open a github issue with the Ray team. [repeated 2x across cluster]
(skyrl_entrypoint pid=364638) 2026-06-12 00:54:01.116 | INFO  | skyrl_train.entrypoints.main_base:_configure_log_level:214 - SkyRL log level set to: INFO
(skyrl_entrypoint pid=364638) The tokenizer you are loading from '/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
(skyrl_entrypoint pid=364638) 2026-06-12 00:54:01.404 | INFO  | examples.terminal_bench.dataset:_load_data_files:40 - Loading data from: /e/scratch/jureap59/feuer1/tasks/exp_rpt_pymethods2test-large
(skyrl_entrypoint pid=364638) 2026-06-12 00:54:04.195 | INFO  | examples.terminal_bench.dataset:_load_data_files:50 - Found 5000 valid task directories out of 5000 total directories
(skyrl_entrypoint pid=364638) 2026-06-12 00:54:04.195 | INFO  | examples.terminal_bench.dataset:__init__:27 - TerminalBenchTaskDataset initialized with 5000 task paths
(skyrl_entrypoint pid=364638) 2026-06-12 00:54:04.206 | INFO  | skyrl_train.entrypoints.main_base:_setup_trainer:407 - data:
(skyrl_entrypoint pid=364638) train_data:
(skyrl_entrypoint pid=364638) - /e/scratch/jureap59/feuer1/tasks/exp_rpt_pymethods2test-large
(skyrl_entrypoint pid=364638) val_data: []
(skyrl_entrypoint pid=364638) trainer:
(skyrl_entrypoint pid=364638) placement:
(skyrl_entrypoint pid=364638) colocate_all: false
(skyrl_entrypoint pid=364638) colocate_policy_ref: true
(skyrl_entrypoint pid=364638) policy_num_nodes: 2
(skyrl_entrypoint pid=364638) policy_num_gpus_per_node: 4
(skyrl_entrypoint pid=364638) critic_num_nodes: 1
(skyrl_entrypoint pid=364638) critic_num_gpus_per_node: 4
(skyrl_entrypoint pid=364638) ref_num_nodes: 2
(skyrl_entrypoint pid=364638) ref_num_gpus_per_node: 4
(skyrl_entrypoint pid=364638) policy_strict_spread_pg: false
(skyrl_entrypoint pid=364638) policy_per_gpu_bundles: false
(skyrl_entrypoint pid=364638) policy_force_cvd_mask: false
(skyrl_entrypoint pid=364638) sequence_parallel_backend: ulysses
(skyrl_entrypoint pid=364638) strategy: fsdp2
(skyrl_entrypoint pid=364638) policy:
(skyrl_entrypoint pid=364638) model:
(skyrl_entrypoint pid=364638) path: /e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6
(skyrl_entrypoint pid=364638) lora:
(skyrl_entrypoint pid=364638) rank: 0
(skyrl_entrypoint pid=364638) alpha: 16
(skyrl_entrypoint pid=364638) dropout: 0
(skyrl_entrypoint pid=364638) lora_sync_path: /tmp/skyrl_lora_sync
(skyrl_entrypoint pid=364638) target_modules: all-linear
(skyrl_entrypoint pid=364638) exclude_modules: null
(skyrl_entrypoint pid=364638) deepspeed_config: ${deepspeed_config.train}
(skyrl_entrypoint pid=364638) optimizer_config:
(skyrl_entrypoint pid=364638) optimizer: AdamW
(skyrl_entrypoint pid=364638) lr: 8.0e-06
(skyrl_entrypoint pid=364638) adam_betas:
(skyrl_entrypoint pid=364638) - 0.9
(skyrl_entrypoint pid=364638) - 0.999
(skyrl_entrypoint pid=364638) weight_decay: 0.0
(skyrl_entrypoint pid=364638) max_grad_norm: 0.9
(skyrl_entrypoint pid=364638) offload_after_step: true
(skyrl_entrypoint pid=364638) num_warmup_steps: 0
(skyrl_entrypoint pid=364638) scheduler: constant_with_warmup
(skyrl_entrypoint pid=364638) optimizer_kwargs: {}
(skyrl_entrypoint pid=364638) fsdp_config:
(skyrl_entrypoint pid=364638) cpu_offload: false
(skyrl_entrypoint pid=364638) reshard_after_forward: true
(skyrl_entrypoint pid=364638) fsdp_size: 4
(skyrl_entrypoint pid=364638) expert_model_parallel_size: 1
(skyrl_entrypoint pid=364638) expert_tensor_parallel_size: 1
(skyrl_entrypoint pid=364638) moe_token_dispatcher_type: alltoall
(skyrl_entrypoint pid=364638) moe_router_replay: false
(skyrl_entrypoint pid=364638) moe_grouped_gemm: false
(skyrl_entrypoint pid=364638) ep_comm_backend: torch
(skyrl_entrypoint pid=364638) deepep_num_sms: 20
(skyrl_entrypoint pid=364638) deepep_token_chunk_size: null
(skyrl_entrypoint pid=364638) sequence_parallel_size: 1
(skyrl_entrypoint pid=364638) use_torch_compile: false
(skyrl_entrypoint pid=364638) record_memory: false
(skyrl_entrypoint pid=364638) megatron_config:
(skyrl_entrypoint pid=364638) tensor_model_parallel_size: 1
(skyrl_entrypoint pid=364638) pipeline_model_parallel_size: 1
(skyrl_entrypoint pid=364638) context_parallel_size: 1
(skyrl_entrypoint pid=364638) expert_model_parallel_size: 1
(skyrl_entrypoint pid=364638) expert_tensor_parallel_size: null
(skyrl_entrypoint pid=364638) ddp_config:
(skyrl_entrypoint pid=364638) grad_reduce_in_fp32: true
(skyrl_entrypoint pid=364638) overlap_grad_reduce: false
(skyrl_entrypoint pid=364638) overlap_param_gather: false
(skyrl_entrypoint pid=364638) average_in_collective: true
(skyrl_entrypoint pid=364638) model_config_kwargs: {}
(skyrl_entrypoint pid=364638) torch_profiler_config:
(skyrl_entrypoint pid=364638) enable: false
(skyrl_entrypoint pid=364638) ranks: []
(skyrl_entrypoint pid=364638) save_path: null
(skyrl_entrypoint pid=364638) optimizer_config_kwargs:
(skyrl_entrypoint pid=364638) overlap_cpu_optimizer_d2h_h2d: false
(skyrl_entrypoint pid=364638) use_precision_aware_optimizer: false
(skyrl_entrypoint pid=364638) optimizer_cpu_offload: false
(skyrl_entrypoint pid=364638) optimizer_offload_fraction: 0.0
(skyrl_entrypoint pid=364638) transformer_config_kwargs:
(skyrl_entrypoint pid=364638) recompute_granularity: full
(skyrl_entrypoint pid=364638) recompute_modules:
(skyrl_entrypoint pid=364638) - core_attn
(skyrl_entrypoint pid=364638) recompute_method: uniform
(skyrl_entrypoint pid=364638) recompute_num_layers: 1
(skyrl_entrypoint pid=364638) empty_cuda_cache: true
(skyrl_entrypoint pid=364638) ref:
(skyrl_entrypoint pid=364638) model:
(skyrl_entrypoint pid=364638) path: ${trainer.policy.model.path}
(skyrl_entrypoint pid=364638) sequence_parallel_size: 1
(skyrl_entrypoint pid=364638) deepspeed_config: ${deepspeed_config.eval}
(skyrl_entrypoint pid=364638) fsdp_config:
(skyrl_entrypoint pid=364638) cpu_offload: false
(skyrl_entrypoint pid=364638) reshard_after_forward: true
(skyrl_entrypoint pid=364638) fsdp_size: 4
(skyrl_entrypoint pid=364638) expert_model_parallel_size: 1
(skyrl_entrypoint pid=364638) expert_tensor_parallel_size: 1
(skyrl_entrypoint pid=364638) moe_token_dispatcher_type: alltoall
(skyrl_entrypoint pid=364638) moe_router_replay: false
(skyrl_entrypoint pid=364638) moe_grouped_gemm: false
(skyrl_entrypoint pid=364638) ep_comm_backend: torch
(skyrl_entrypoint pid=364638) deepep_num_sms: 20
(skyrl_entrypoint pid=364638) deepep_token_chunk_size: null
(skyrl_entrypoint pid=364638) megatron_config:
(skyrl_entrypoint pid=364638) tensor_model_parallel_size: 1
(skyrl_entrypoint pid=364638) pipeline_model_parallel_size: 1
(skyrl_entrypoint pid=364638) context_parallel_size: 1
(skyrl_entrypoint pid=364638) expert_model_parallel_size: 1
(skyrl_entrypoint pid=364638) expert_tensor_parallel_size: 1
(skyrl_entrypoint pid=364638) model_config_kwargs: {}
(skyrl_entrypoint pid=364638) transformer_config_kwargs: {}
(skyrl_entrypoint pid=364638) critic:
(skyrl_entrypoint pid=364638) model:
(skyrl_entrypoint pid=364638) path: null
(skyrl_entrypoint pid=364638) lora:
(skyrl_entrypoint pid=364638) rank: 0
(skyrl_entrypoint pid=364638) alpha: 16
(skyrl_entrypoint pid=364638) dropout: 0
(skyrl_entrypoint pid=364638) target_modules: all-linear
(skyrl_entrypoint pid=364638) exclude_modules: null
(skyrl_entrypoint pid=364638) deepspeed_config: ${deepspeed_config.train}
(skyrl_entrypoint pid=364638) optimizer_config:
(skyrl_entrypoint pid=364638) optimizer: AdamW
(skyrl_entrypoint pid=364638) lr: 5.0e-06
(skyrl_entrypoint pid=364638) adam_betas:
(skyrl_entrypoint pid=364638) - 0.9
(skyrl_entrypoint pid=364638) - 0.999
(skyrl_entrypoint pid=364638) weight_decay: 0.01
(skyrl_entrypoint pid=364638) max_grad_norm: 1.0
(skyrl_entrypoint pid=364638) offload_after_step: true
(skyrl_entrypoint pid=364638) num_warmup_steps: 0
(skyrl_entrypoint pid=364638) scheduler: constant_with_warmup
(skyrl_entrypoint pid=364638) optimizer_kwargs: {}
(skyrl_entrypoint pid=364638) fsdp_config:
(skyrl_entrypoint pid=364638) cpu_offload: false
(skyrl_entrypoint pid=364638) reshard_after_forward: true
(skyrl_entrypoint pid=364638) fsdp_size: -1
(skyrl_entrypoint pid=364638) expert_model_parallel_size: 1
(skyrl_entrypoint pid=364638) expert_tensor_parallel_size: 1
(skyrl_entrypoint pid=364638) moe_token_dispatcher_type: alltoall
(skyrl_entrypoint pid=364638) moe_router_replay: false
(skyrl_entrypoint pid=364638) moe_grouped_gemm: false
(skyrl_entrypoint pid=364638) ep_comm_backend: torch
(skyrl_entrypoint pid=364638) deepep_num_sms: 20
(skyrl_entrypoint pid=364638) deepep_token_chunk_size: null
(skyrl_entrypoint pid=364638) sequence_parallel_size: 1
(skyrl_entrypoint pid=364638) algorithm:
(skyrl_entrypoint pid=364638) advantage_estimator: rloo_n
(skyrl_entrypoint pid=364638) kl_ctrl:
(skyrl_entrypoint pid=364638) type: fixed
(skyrl_entrypoint pid=364638) kl_target: 0.1
(skyrl_entrypoint pid=364638) horizon: 10000
(skyrl_entrypoint pid=364638) kl_estimator_type: k3
(skyrl_entrypoint pid=364638) use_kl_estimator_k3: false
(skyrl_entrypoint pid=364638) use_abs_kl: false
(skyrl_entrypoint pid=364638) use_kl_in_reward: false
(skyrl_entrypoint pid=364638) use_kl_loss: false
(skyrl_entrypoint pid=364638) kl_loss_coef: 0.0
(skyrl_entrypoint pid=364638) use_entropy_loss: false
(skyrl_entrypoint pid=364638) entropy_loss_coef: 0.01
(skyrl_entrypoint pid=364638) advantage_batch_normalize: false
(skyrl_entrypoint pid=364638) value_head_prefix: value_head
(skyrl_entrypoint pid=364638) policy_loss_type: regular
(skyrl_entrypoint pid=364638) loss_reduction: seq_mean_token_sum_norm_global
(skyrl_entrypoint pid=364638) global_loss_denom: null
(skyrl_entrypoint pid=364638) grpo_norm_by_std: true
(skyrl_entrypoint pid=364638) rloo_n_min_group_size: 4
(skyrl_entrypoint pid=364638) rloo_n_filter_zero_reward_groups: true
(skyrl_entrypoint pid=364638) lambd: 1.0
(skyrl_entrypoint pid=364638) gamma: 1.0
(skyrl_entrypoint pid=364638) eps_clip_low: 0.2
(skyrl_entrypoint pid=364638) eps_clip_high: 0.05
(skyrl_entrypoint pid=364638) clip_ratio_c: 3.0
(skyrl_entrypoint pid=364638) tis_imp_ratio_cap: 2.0
(skyrl_entrypoint pid=364638) use_tis: true
(skyrl_entrypoint pid=364638) sapo:
(skyrl_entrypoint pid=364638) tau_pos: 1.0
(skyrl_entrypoint pid=364638) tau_neg: 1.05
(skyrl_entrypoint pid=364638) value_clip: 0.2
(skyrl_entrypoint pid=364638) dynamic_sampling:
(skyrl_entrypoint pid=364638) type: null
(skyrl_entrypoint pid=364638) max_sample_batches: 30
(skyrl_entrypoint pid=364638) min_replace_ratio: 0.3
(skyrl_entrypoint pid=364638) clip_cov:
(skyrl_entrypoint pid=364638) clip_ratio: 0.0002
(skyrl_entrypoint pid=364638) clip_cov_lb: 1.0
(skyrl_entrypoint pid=364638) clip_cov_ub: 5.0
(skyrl_entrypoint pid=364638) kl_cov:
(skyrl_entrypoint pid=364638) kl_cov_frac: 0.2
(skyrl_entrypoint pid=364638) ppo_kl_coef: 1.0
(skyrl_entrypoint pid=364638) cispo:
(skyrl_entrypoint pid=364638) cispo_eps_clip_low: 0
(skyrl_entrypoint pid=364638) cispo_eps_clip_high: 5
(skyrl_entrypoint pid=364638) z_clip:
(skyrl_entrypoint pid=364638) enabled: false
(skyrl_entrypoint pid=364638) alpha: 0.97
(skyrl_entrypoint pid=364638) z_thresh: 2.5
(skyrl_entrypoint pid=364638) warmup_steps: 25
(skyrl_entrypoint pid=364638) mode: zscore
(skyrl_entrypoint pid=364638) clip_option: adaptive_scaling
(skyrl_entrypoint pid=364638) clip_factor: 1.0
(skyrl_entrypoint pid=364638) skip_update_on_spike: false
(skyrl_entrypoint pid=364638) stale_clip:
(skyrl_entrypoint pid=364638) enabled: false
(skyrl_entrypoint pid=364638) alpha: 0.3
(skyrl_entrypoint pid=364638) entropy_threshold: 0.15
(skyrl_entrypoint pid=364638) entropy_window: 10
(skyrl_entrypoint pid=364638) min_lr_scale: 0.1
(skyrl_entrypoint pid=364638) max_seq_len: 1004095
(skyrl_entrypoint pid=364638) fully_async:
(skyrl_entrypoint pid=364638) max_staleness_steps: 16
(skyrl_entrypoint pid=364638) num_parallel_generation_workers: 338
(skyrl_entrypoint pid=364638) gradient_checkpointing: true
(skyrl_entrypoint pid=364638) gradient_checkpointing_use_reentrant: false
(skyrl_entrypoint pid=364638) seed: 42
(skyrl_entrypoint pid=364638) resume_mode: latest
(skyrl_entrypoint pid=364638) resume_path: null
(skyrl_entrypoint pid=364638) ckpt_path: /e/data1/datasets/playground/ot-baf/explore-tis-untrunc/explore-tis-untrunc/checkpoints
(skyrl_entrypoint pid=364638) max_ckpts_to_keep: -1
(skyrl_entrypoint pid=364638) ckpt_interval: 2
(skyrl_entrypoint pid=364638) hf_save_interval: 5
(skyrl_entrypoint pid=364638) hf_upload_mode: latest
(skyrl_entrypoint pid=364638) export_path: /e/data1/datasets/playground/ot-baf/explore-tis-untrunc/explore-tis-untrunc/exports
(skyrl_entrypoint pid=364638) bf16: true
(skyrl_entrypoint pid=364638) epochs: 2
(skyrl_entrypoint pid=364638) max_steps: 80
(skyrl_entrypoint pid=364638) update_epochs_per_batch: 1
(skyrl_entrypoint pid=364638) train_batch_size: 64
(skyrl_entrypoint pid=364638) policy_mini_batch_size: 64
(skyrl_entrypoint pid=364638) critic_mini_batch_size: 256
(skyrl_entrypoint pid=364638) micro_train_batch_size_per_gpu: 1
(skyrl_entrypoint pid=364638) micro_forward_batch_size_per_gpu: 4
(skyrl_entrypoint pid=364638) update_ref_every_epoch: false
(skyrl_entrypoint pid=364638) use_sample_packing: true
(skyrl_entrypoint pid=364638) eval_batch_size: 64
(skyrl_entrypoint pid=364638) eval_before_train: false
(skyrl_entrypoint pid=364638) eval_interval: 999999
(skyrl_entrypoint pid=364638) max_prompt_length: 999999
(skyrl_entrypoint pid=364638) flash_attn: true
(skyrl_entrypoint pid=364638) disable_fast_tokenizer: false
(skyrl_entrypoint pid=364638) target_modules: null
(skyrl_entrypoint pid=364638) exclude_modules: null
(skyrl_entrypoint pid=364638) project_name: OpenThoughts-Agent
(skyrl_entrypoint pid=364638) run_name: explore-tis-untrunc
(skyrl_entrypoint pid=364638) logger: console
(skyrl_entrypoint pid=364638) tracker_commit_each_step: true
(skyrl_entrypoint pid=364638) dump_data_batch: false
(skyrl_entrypoint pid=364638) dump_eval_results: true
(skyrl_entrypoint pid=364638) log_level: INFO
(skyrl_entrypoint pid=364638) rope_scaling: null
(skyrl_entrypoint pid=364638) rope_theta: null
(skyrl_entrypoint pid=364638) step_wise_training: false
(skyrl_entrypoint pid=364638) hf_hub_repo_id: laion/explore-tis-untrunc
(skyrl_entrypoint pid=364638) hf_hub_private: false
(skyrl_entrypoint pid=364638) hf_hub_revision: main
(skyrl_entrypoint pid=364638) enable_db_registration: false
(skyrl_entrypoint pid=364638) generator:
(skyrl_entrypoint pid=364638) model_name: ${trainer.policy.model.path}
(skyrl_entrypoint pid=364638) model_dtype: bfloat16
(skyrl_entrypoint pid=364638) timeout_multiplier: 1.0
(skyrl_entrypoint pid=364638) run_engines_locally: true
(skyrl_entrypoint pid=364638) num_inference_engines: 48
(skyrl_entrypoint pid=364638) backend: vllm
(skyrl_entrypoint pid=364638) weight_sync_backend: nccl
(skyrl_entrypoint pid=364638) fuse_weights: false
(skyrl_entrypoint pid=364638) weight_transfer_threshold_cuda_ipc_GB: 1.0
(skyrl_entrypoint pid=364638) inference_engine_tensor_parallel_size: 1
(skyrl_entrypoint pid=364638) inference_engine_pipeline_parallel_size: 1
(skyrl_entrypoint pid=364638) inference_engine_expert_parallel_size: 1
(skyrl_entrypoint pid=364638) inference_engine_data_parallel_size: 1
(skyrl_entrypoint pid=364638) inference_engine_mp_backend: false
(skyrl_entrypoint pid=364638) n_samples_per_prompt: 8
(skyrl_entrypoint pid=364638) async_engine: true
(skyrl_entrypoint pid=364638) batched: false
(skyrl_entrypoint pid=364638) max_input_length: ${trainer.max_prompt_length}
(skyrl_entrypoint pid=364638) vllm_v1_disable_multiproc: true
(skyrl_entrypoint pid=364638) enable_prefix_caching: true
(skyrl_entrypoint pid=364638) enable_chunked_prefill: true
(skyrl_entrypoint pid=364638) max_num_batched_tokens: 65536
(skyrl_entrypoint pid=364638) enforce_eager: true
(skyrl_entrypoint pid=364638) fully_sharded_loras: false
(skyrl_entrypoint pid=364638) enable_ray_prometheus_stats: false
(skyrl_entrypoint pid=364638) vllm_stats_interval: 1
(skyrl_entrypoint pid=364638) gpu_memory_utilization: 0.75
(skyrl_entrypoint pid=364638) max_num_seqs: 24
(skyrl_entrypoint pid=364638) remote_inference_engine_urls:
(skyrl_entrypoint pid=364638) - 127.0.0.1:8001
(skyrl_entrypoint pid=364638) enable_http_endpoint: true
(skyrl_entrypoint pid=364638) http_endpoint_host: 127.0.0.1
(skyrl_entrypoint pid=364638) http_endpoint_port: 8000
(skyrl_entrypoint pid=364638) max_turns: 999999
(skyrl_entrypoint pid=364638) chat_template:
(skyrl_entrypoint pid=364638) source: name
(skyrl_entrypoint pid=364638) name_or_path: null
(skyrl_entrypoint pid=364638) chat_template_kwargs: {}
(skyrl_entrypoint pid=364638) engine_init_kwargs:
(skyrl_entrypoint pid=364638) max_model_len: 32768
(skyrl_entrypoint pid=364638) custom_chat_template_chat_completion_path: chat_templates/qwen3_thinking_acc.jinja2
(skyrl_entrypoint pid=364638) served_model_name: 0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6
(skyrl_entrypoint pid=364638) override_existing_update_group: disable
(skyrl_entrypoint pid=364638) sampling_params:
(skyrl_entrypoint pid=364638) max_generate_length: 4096
(skyrl_entrypoint pid=364638) repetition_penalty: 1.0
(skyrl_entrypoint pid=364638) temperature: 1.0
(skyrl_entrypoint pid=364638) top_p: 1.0
(skyrl_entrypoint pid=364638) min_p: 0.0
(skyrl_entrypoint pid=364638) top_k: -1
(skyrl_entrypoint pid=364638) logprobs: 0
(skyrl_entrypoint pid=364638) stop: null
(skyrl_entrypoint pid=364638) use_conversation_multi_turn: true
(skyrl_entrypoint pid=364638) append_eos_token_after_stop_str_in_multi_turn: true
(skyrl_entrypoint pid=364638) eval_sampling_params:
(skyrl_entrypoint pid=364638) max_generate_length: ${generator.sampling_params.max_generate_length}
(skyrl_entrypoint pid=364638) repetition_penalty: 1.0
(skyrl_entrypoint pid=364638) temperature: 0.0
(skyrl_entrypoint pid=364638) top_p: 1.0
(skyrl_entrypoint pid=364638) min_p: 0.0
(skyrl_entrypoint pid=364638) top_k: -1
(skyrl_entrypoint pid=364638) logprobs: null
(skyrl_entrypoint pid=364638) stop: null
(skyrl_entrypoint pid=364638) eval_n_samples_per_prompt: 8
(skyrl_entrypoint pid=364638) zero_reward_on_non_stop: false
(skyrl_entrypoint pid=364638) apply_overlong_filtering: false
(skyrl_entrypoint pid=364638) rope_scaling: ${trainer.rope_scaling}
(skyrl_entrypoint pid=364638) rope_theta: ${trainer.rope_theta}
(skyrl_entrypoint pid=364638) teacher:
(skyrl_entrypoint pid=364638) model_path: null
(skyrl_entrypoint pid=364638) top_k_logprobs: 256
(skyrl_entrypoint pid=364638) num_inference_engines: 1
(skyrl_entrypoint pid=364638) inference_engine_tensor_parallel_size: 1
(skyrl_entrypoint pid=364638) inference_engine_pipeline_parallel_size: 1
(skyrl_entrypoint pid=364638) gpu_memory_utilization: 0.9
(skyrl_entrypoint pid=364638) enforce_eager: false
(skyrl_entrypoint pid=364638) backend: vllm
(skyrl_entrypoint pid=364638) engine_init_kwargs: {}
(skyrl_entrypoint pid=364638) environment:
(skyrl_entrypoint pid=364638) env_class: gsm8k
(skyrl_entrypoint pid=364638) skyrl_gym:
(skyrl_entrypoint pid=364638) max_env_workers: 32
(skyrl_entrypoint pid=364638) text2sql:
(skyrl_entrypoint pid=364638) db_path: /home/ray/default/sql_data
(skyrl_entrypoint pid=364638) llm_as_a_judge:
(skyrl_entrypoint pid=364638) model: gpt-4o-mini
(skyrl_entrypoint pid=364638) base_url: null
(skyrl_entrypoint pid=364638) search:
(skyrl_entrypoint pid=364638) log_requests: false
(skyrl_entrypoint pid=364638) search_url: http://127.0.0.1:8000/retrieve
(skyrl_entrypoint pid=364638) topk: 3
(skyrl_entrypoint pid=364638) timeout: 30
(skyrl_entrypoint pid=364638) rollout:
(skyrl_entrypoint pid=364638) fanout:
(skyrl_entrypoint pid=364638) enabled: true
(skyrl_entrypoint pid=364638) num_coordinators: 4
(skyrl_entrypoint pid=364638) cpus_per_coordinator: 8
(skyrl_entrypoint pid=364638) deepspeed_config:
(skyrl_entrypoint pid=364638) train:
(skyrl_entrypoint pid=364638) zero_optimization:
(skyrl_entrypoint pid=364638) stage: 3
(skyrl_entrypoint pid=364638) offload_param:
(skyrl_entrypoint pid=364638) device: none
(skyrl_entrypoint pid=364638) offload_optimizer:
(skyrl_entrypoint pid=364638) device: none
(skyrl_entrypoint pid=364638) pin_memory: true
(skyrl_entrypoint pid=364638) sub_group_size: auto
(skyrl_entrypoint pid=364638) reduce_bucket_size: auto
(skyrl_entrypoint pid=364638) stage3_param_persistence_threshold: auto
(skyrl_entrypoint pid=364638) stage3_prefetch_bucket_size: auto
(skyrl_entrypoint pid=364638) stage3_max_live_parameters: auto
(skyrl_entrypoint pid=364638) stage3_max_reuse_distance: auto
(skyrl_entrypoint pid=364638) round_robin_gradients: true
(skyrl_entrypoint pid=364638) zero_hpz_partition_size: 1
(skyrl_entrypoint pid=364638) zero_quantized_weights: false
(skyrl_entrypoint pid=364638) zero_quantized_gradients: false
(skyrl_entrypoint pid=364638) torch_autocast:
(skyrl_entrypoint pid=364638) enabled: true
(skyrl_entrypoint pid=364638) dtype: bfloat16
(skyrl_entrypoint pid=364638) disable_trace_cache: false
(skyrl_entrypoint pid=364638) data_types:
(skyrl_entrypoint pid=364638) grad_accum_dtype: fp32
(skyrl_entrypoint pid=364638) gradient_clipping: 1.0
(skyrl_entrypoint pid=364638) wall_clock_breakdown: false
(skyrl_entrypoint pid=364638) prescale_gradient: false
(skyrl_entrypoint pid=364638) eval:
(skyrl_entrypoint pid=364638) zero_optimization:
(skyrl_entrypoint pid=364638) stage: 3
(skyrl_entrypoint pid=364638) stage3_param_persistence_threshold: auto
(skyrl_entrypoint pid=364638) offload_param:
(skyrl_entrypoint pid=364638) device: cpu
(skyrl_entrypoint pid=364638) pin_memory: true
(skyrl_entrypoint pid=364638) torch_autocast:
(skyrl_entrypoint pid=364638) enabled: true
(skyrl_entrypoint pid=364638) dtype: bfloat16
(skyrl_entrypoint pid=364638) gradient_clipping: 1.0
(skyrl_entrypoint pid=364638) prescale_gradient: false
(skyrl_entrypoint pid=364638) wall_clock_breakdown: false
(skyrl_entrypoint pid=364638) terminal_bench_config:
(skyrl_entrypoint pid=364638) trials_dir: /e/data1/datasets/playground/ot-baf/explore-tis-untrunc/explore-tis-untrunc/trace_jobs
(skyrl_entrypoint pid=364638) harbor:
(skyrl_entrypoint pid=364638) name: terminus-2
(skyrl_entrypoint pid=364638) max_episodes: 999999
(skyrl_entrypoint pid=364638) enable_summarize: false
(skyrl_entrypoint pid=364638) store_all_messages: true
(skyrl_entrypoint pid=364638) trajectory_config:
(skyrl_entrypoint pid=364638) raw_content: true
(skyrl_entrypoint pid=364638) enable_episode_logging: false
(skyrl_entrypoint pid=364638) record_terminal_session: false
(skyrl_entrypoint pid=364638) enable_pane_logging: false
(skyrl_entrypoint pid=364638) strict_json_parser: true
(skyrl_entrypoint pid=364638) interleaved_thinking: true
(skyrl_entrypoint pid=364638) extra_body:
(skyrl_entrypoint pid=364638) chat_template_kwargs:
(skyrl_entrypoint pid=364638) enable_thinking: true
(skyrl_entrypoint pid=364638) override_timeout_sec: 900
(skyrl_entrypoint pid=364638) override_cpus: 1
(skyrl_entrypoint pid=364638) override_memory_mb: 2048
(skyrl_entrypoint pid=364638) override_storage_mb: 2048
(skyrl_entrypoint pid=364638) auto_snapshot: true
(skyrl_entrypoint pid=364638) verifier_override_timeout_sec: 120
(skyrl_entrypoint pid=364638) max_retries: 3
(skyrl_entrypoint pid=364638) min_wait_sec: 60.0
(skyrl_entrypoint pid=364638) max_wait_sec: 600.0
(skyrl_entrypoint pid=364638) wait_multiplier: 2.0
(skyrl_entrypoint pid=364638) exclude_exceptions:
(skyrl_entrypoint pid=364638) - VerifierTimeoutError
(skyrl_entrypoint pid=364638) - VerifierRuntimeError
(skyrl_entrypoint pid=364638) - RewardFileNotFoundError
(skyrl_entrypoint pid=364638) - RewardFileEmptyError
(skyrl_entrypoint pid=364638) - VerifierOutputParseError
(skyrl_entrypoint pid=364638) n_concurrent_trials: 675
(skyrl_entrypoint pid=364638) log_level: INFO
(skyrl_entrypoint pid=364638) enable_reward_shaping: false
(skyrl_entrypoint pid=364638) collect_rollout_details: true
(skyrl_entrypoint pid=364638) enable_error_classification: true
(skyrl_entrypoint pid=364638) mask_exceptions:
(skyrl_entrypoint pid=364638) - DaytonaError
(skyrl_entrypoint pid=364638) - EnvironmentStartTimeoutError
(skyrl_entrypoint pid=364638) - NetworkError
(skyrl_entrypoint pid=364638) - ConnectionError
(skyrl_entrypoint pid=364638) - RewardFileNotFoundError
(skyrl_entrypoint pid=364638) - RewardFileEmptyError
(skyrl_entrypoint pid=364638) - AgentEnvironmentTimeoutError
(skyrl_entrypoint pid=364638) - ContextLengthExceededError
(skyrl_entrypoint pid=364638) default_error_treatment: zero
(skyrl_entrypoint pid=364638) passthrough_exceptions:
(skyrl_entrypoint pid=364638) - AgentTimeoutError
(skyrl_entrypoint pid=364638) zero_exceptions: []
(skyrl_entrypoint pid=364638) model_info:
(skyrl_entrypoint pid=364638) max_input_tokens: 32000
(skyrl_entrypoint pid=364638) max_output_tokens: 4096
(skyrl_entrypoint pid=364638) archiving:
(skyrl_entrypoint pid=364638) enabled: false
(skyrl_entrypoint pid=364638) trace_upload:
(skyrl_entrypoint pid=364638) enabled: true
(skyrl_entrypoint pid=364638) repo_org: DCAgent
(skyrl_entrypoint pid=364638) episodes: last
(skyrl_entrypoint pid=364638) dataset_type: SFT
(skyrl_entrypoint pid=364638) cleanup: true
(skyrl_entrypoint pid=364638) 
(pid=348197) [2026-06-12 00:54:01,724 E 348197 363053] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14 [repeated 268x across cluster]
(skyrl_entrypoint pid=364638) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/vllm/__init__.py:7: RuntimeWarning: Failed to read commit hash:
(skyrl_entrypoint pid=364638) No module named 'vllm._version'
(skyrl_entrypoint pid=364638) from .version import __version__, __version_tuple__ # isort:skip
(skyrl_entrypoint pid=364638) W0612 00:54:09.087000 364638 envs/rl/lib/python3.12/site-packages/torch/utils/cpp_extension.py:117] No CUDA runtime is found, using CUDA_HOME='/e/software/default/stages/2026/software/CUDA/13'
(raylet) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e
(raylet) 2026-06-12 00:54:12,109 WARNING node.py:1846 -- The object spilling config is specified from an unstable API - system config or environment variable. This is subject to change in the future. You can use the stable API - --object-spilling-directory in ray start or object_spilling_directory in ray.init() to specify the object spilling directory instead. If you need more advanced settings, please open a github issue with the Ray team.
(raylet, ip=10.128.25.23) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 41x across cluster]
(raylet, ip=10.128.25.23) 2026-06-12 00:54:16,191 WARNING node.py:1846 -- The object spilling config is specified from an unstable API - system config or environment variable. This is subject to change in the future. You can use the stable API - --object-spilling-directory in ray start or object_spilling_directory in ray.init() to specify the object spilling directory instead. If you need more advanced settings, please open a github issue with the Ray team. [repeated 6x across cluster]
(pid=478659, ip=10.128.25.176) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/vllm/__init__.py:7: RuntimeWarning: Failed to read commit hash:
(pid=478659, ip=10.128.25.176) No module named 'vllm._version'
(pid=478659, ip=10.128.25.176) from .version import __version__, __version_tuple__ # isort:skip
(raylet, ip=10.128.25.161) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 78x across cluster]
[2026-06-12 00:54:22,401 E 364224 364547] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14
(raylet, ip=10.128.25.162) 2026-06-12 00:54:21,909 WARNING node.py:1846 -- The object spilling config is specified from an unstable API - system config or environment variable. This is subject to change in the future. You can use the stable API - --object-spilling-directory in ray start or object_spilling_directory in ray.init() to specify the object spilling directory instead. If you need more advanced settings, please open a github issue with the Ray team. [repeated 18x across cluster]
(pid=316063, ip=10.128.25.23) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/vllm/__init__.py:7: RuntimeWarning: Failed to read commit hash: [repeated 3x across cluster]
(pid=316063, ip=10.128.25.23) No module named 'vllm._version' [repeated 3x across cluster]
(pid=316063, ip=10.128.25.23) from .version import __version__, __version_tuple__ # isort:skip [repeated 3x across cluster]
(RegistryActor pid=364573) [2026-06-12 00:54:23,544 E 364573 364613] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14
(raylet, ip=10.128.25.163) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 90x across cluster]
(raylet, ip=10.128.25.174) 2026-06-12 00:54:27,918 WARNING node.py:1846 -- The object spilling config is specified from an unstable API - system config or environment variable. This is subject to change in the future. You can use the stable API - --object-spilling-directory in ray start or object_spilling_directory in ray.init() to specify the object spilling directory instead. If you need more advanced settings, please open a github issue with the Ray team. [repeated 12x across cluster]
(pid=249226, ip=10.128.25.24) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/vllm/__init__.py:7: RuntimeWarning: Failed to read commit hash: [repeated 20x across cluster]
(pid=249226, ip=10.128.25.24) No module named 'vllm._version' [repeated 20x across cluster]
(pid=249226, ip=10.128.25.24) from .version import __version__, __version_tuple__ # isort:skip [repeated 20x across cluster]
(skyrl_entrypoint pid=364638) [2026-06-12 00:54:25,383 E 364638 364681] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14 [repeated 2x across cluster]
(raylet, ip=10.128.25.165) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 56x across cluster]
(raylet, ip=10.128.25.28) 2026-06-12 00:54:32,714 WARNING node.py:1846 -- The object spilling config is specified from an unstable API - system config or environment variable. This is subject to change in the future. You can use the stable API - --object-spilling-directory in ray start or object_spilling_directory in ray.init() to specify the object spilling directory instead. If you need more advanced settings, please open a github issue with the Ray team. [repeated 9x across cluster]
(pid=443231, ip=10.128.25.174) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/vllm/__init__.py:7: RuntimeWarning: Failed to read commit hash: [repeated 4x across cluster]
(pid=443231, ip=10.128.25.174) No module named 'vllm._version' [repeated 4x across cluster]
(pid=443231, ip=10.128.25.174) from .version import __version__, __version_tuple__ # isort:skip [repeated 4x across cluster]
(skyrl_entrypoint pid=364638) [2026-06-12 00:54:36] INFO inference_engine_client_http_endpoint.py:350: Starting server on 0.0.0.0:8000
(skyrl_entrypoint pid=364638) [2026-06-12 00:54:36] INFO inference_engine_client_http_endpoint.py:242: Starting inference HTTP endpoint...
(skyrl_entrypoint pid=364638) [2026-06-12 00:54:37] INFO inference_engine_client_http_endpoint.py:229: Server ready after 2 attempts (2 seconds)
(skyrl_entrypoint pid=364638) 2026-06-12 00:54:37.317 | INFO  | skyrl_train.inference_engines.inference_engine_client:_spin_up_http_endpoint:969 - InferenceEngineClient HTTP endpoint started on 127.0.0.1:8000
(skyrl_entrypoint pid=364638) 2026-06-12 00:54:37.317 | INFO  | skyrl_train.inference_engines.inference_engine_client:__init__:61 - InferenceEngineClient initialized with 48 engines.
(skyrl_entrypoint pid=364638) 2026-06-12 00:54:37.319 | INFO  | examples.terminal_bench.terminal_bench_generator:_configure_harbor_logging:242 - Harbor logging level set to INFO
(skyrl_entrypoint pid=364638) 2026-06-12 00:54:37.320 | INFO  | examples.terminal_bench.terminal_bench_generator:__init__:142 - TerminalBenchGenerator initialized with HarborConfigBuilder. Exposed fields: ['name', 'max_episodes', 'enable_summarize', 'store_all_messages', 'trajectory_config', 'enable_episode_logging', 'record_terminal_session', 'enable_pane_logging', 'strict_json_parser', 'interleaved_thinking', 'extra_body', 'override_timeout_sec', 'override_cpus', 'override_memory_mb', 'override_storage_mb', 'auto_snapshot', 'verifier_override_timeout_sec', 'max_retries', 'min_wait_sec', 'max_wait_sec', 'wait_multiplier', 'exclude_exceptions', 'n_concurrent_trials', 'log_level', 'enable_reward_shaping', 'collect_rollout_details', 'enable_error_classification', 'mask_exceptions', 'default_error_treatment', 'passthrough_exceptions', 'zero_exceptions']. Retry config: max_retries=3, backoff=60.0-600.0s. Concurrent trials: 675. Reward shaping: enabled=False, shaper=pass_ratio. Error classification: enabled=True
(skyrl_entrypoint pid=364638) 2026-06-12 00:54:37.321 | INFO  | examples.terminal_bench.terminal_bench_generator:__init__:158 - TerminalBenchGenerator initialized with custom chat template read from: chat_templates/qwen3_thinking_acc.jinja2
(skyrl_entrypoint pid=364638) 2026-06-12 00:54:37.322 | INFO  | skyrl_train.utils.trainer_utils:build_dataloader:656 - Total steps: 156
(skyrl_entrypoint pid=364638) 2026-06-12 00:54:37.322 | INFO  | skyrl_train.fully_async_trainer:_build_train_dataloader_and_compute_training_steps:357 - Length of train_dataloader: 5000
(skyrl_entrypoint pid=364638) 2026-06-12 00:54:37.322 | INFO  | skyrl_train.fully_async_trainer:_build_train_dataloader_and_compute_training_steps:358 - Number of steps per epoch: 78
(skyrl_entrypoint pid=364638) 2026-06-12 00:54:37.322 | INFO  | skyrl_train.fully_async_trainer:_build_train_dataloader_and_compute_training_steps:359 - Total training steps: 80
(raylet, ip=10.128.25.27) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 100x across cluster]
(bundle_reservation_check_func pid=364729) [2026-06-12 00:54:42,131 E 364729 364769] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14
(raylet, ip=10.128.25.172) 2026-06-12 00:54:38,341 WARNING node.py:1846 -- The object spilling config is specified from an unstable API - system config or environment variable. This is subject to change in the future. You can use the stable API - --object-spilling-directory in ray start or object_spilling_directory in ray.init() to specify the object spilling directory instead. If you need more advanced settings, please open a github issue with the Ray team. [repeated 16x across cluster]
(pid=326289, ip=10.128.25.27) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/vllm/__init__.py:7: RuntimeWarning: Failed to read commit hash: [repeated 20x across cluster]
(pid=326289, ip=10.128.25.27) No module named 'vllm._version' [repeated 20x across cluster]
(pid=326289, ip=10.128.25.27) from .version import __version__, __version_tuple__ # isort:skip [repeated 20x across cluster]
(pid=441858, ip=10.128.25.172) Using blocking ray.get inside async actor. This blocks the event loop. Please use `await` on object ref with asyncio.gather if you want to yield execution to the event loop instead.
(raylet, ip=10.128.25.172) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 7x across cluster]
(pid=316064, ip=10.128.25.23) [2026-06-12 00:54:48,004 E 316064 316166] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14 [repeated 7x across cluster]
(pid=300698, ip=10.128.25.162) [2026-06-12 00:54:53,488 E 300698 300807] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14 [repeated 18x across cluster]
(pid=443232, ip=10.128.25.174) [2026-06-12 00:54:59,702 E 443232 443308] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14 [repeated 12x across cluster]
(pid=305554, ip=10.128.25.164) [2026-06-12 00:55:06,467 E 305554 305664] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14 [repeated 18x across cluster]
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) 2026-06-12 00:57:02.324 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:setup_envvars_for_vllm:152 - setup_envvars_for_vllm: distributed_executor_backend=uni, SKYRL_ENABLE_NUMA_AFFINITY=1, CUDA_VISIBLE_DEVICES=0, VLLM_ENABLE_V1_MULTIPROCESSING=<unset>
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) 2026-06-12 00:57:02.338 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:setup_envvars_for_vllm:167 - setup_envvars_for_vllm: numa_enabled=True
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) 2026-06-12 00:57:02.338 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:setup_envvars_for_vllm:170 - setup_envvars_for_vllm: set VLLM_ENABLE_V1_MULTIPROCESSING=0 for NUMA affinity
(pid=441858, ip=10.128.25.172) [2026-06-12 00:55:08,360 E 441858 441898] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14 [repeated 6x across cluster]
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) 2026-06-12 00:57:03.476 | INFO | skyrl_train.utils.numa:set_numa_affinity_for_gpu:340 - NUMA affinity: bound process to CPUs 0-71 (NUMA node 0) for GPU 0
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) 2026-06-12 00:57:03.499 | DEBUG | skyrl_train.utils.numa:_set_membind_via_libnuma:375 - NUMA affinity: set memory preferred to NUMA node 0
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) 2026-06-12 00:57:03.499 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:__init__:618 - BaseVLLMInferenceEngine: vllm_v1_disable_multiproc=True, vllm.__version__=dev, VLLM_ENABLE_V1_MULTIPROCESSING=0
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) 2026-06-12 00:57:03.499 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:__init__:626 - BaseVLLMInferenceEngine: set VLLM_ENABLE_V1_MULTIPROCESSING=0
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) 2026-06-12 00:57:03.499 | WARNING | skyrl_train.inference_engines.vllm.vllm_engine:_create_engine:1192 - OpenAI API sampling params overridden: temperature=1.0, top_p=1.0, top_k=-1
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) 2026-06-12 00:57:03.546 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:_create_engine:1244 - Engine startup stagger: sleeping 2.14s (attempt 1/5) to avoid port collisions
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored.
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored.
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) The tokenizer you are loading from '/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/vllm/__init__.py:7: RuntimeWarning: Failed to read commit hash:
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) No module named 'vllm._version'
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) from .version import __version__, __version_tuple__ # isort:skip
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) 2026-06-12 00:57:03.392 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:setup_envvars_for_vllm:152 - setup_envvars_for_vllm: distributed_executor_backend=uni, SKYRL_ENABLE_NUMA_AFFINITY=1, CUDA_VISIBLE_DEVICES=3, VLLM_ENABLE_V1_MULTIPROCESSING=<unset> [repeated 47x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) 2026-06-12 00:57:03.393 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:setup_envvars_for_vllm:167 - setup_envvars_for_vllm: numa_enabled=True [repeated 47x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) 2026-06-12 00:57:03.394 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:setup_envvars_for_vllm:170 - setup_envvars_for_vllm: set VLLM_ENABLE_V1_MULTIPROCESSING=0 for NUMA affinity [repeated 47x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) 2026-06-12 00:57:08 INFO [ipv4-debug] hostname=jpbo-029-44.jupiter.internal
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) 2026-06-12 00:57:08 INFO [ipv4-debug] _global_node.node_ip_address=10.128.25.172
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) 2026-06-12 00:57:08 INFO [ipv4-debug] get_node_ip_address()=10.128.25.172
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) 2026-06-12 00:57:04.715 | INFO | skyrl_train.utils.numa:set_numa_affinity_for_gpu:340 - NUMA affinity: bound process to CPUs 216-287 (NUMA node 3) for GPU 3 [repeated 47x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) 2026-06-12 00:57:04.731 | DEBUG | skyrl_train.utils.numa:_set_membind_via_libnuma:375 - NUMA affinity: set memory preferred to NUMA node 3 [repeated 47x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) 2026-06-12 00:57:04.731 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:__init__:618 - BaseVLLMInferenceEngine: vllm_v1_disable_multiproc=True, vllm.__version__=dev, VLLM_ENABLE_V1_MULTIPROCESSING=0 [repeated 47x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) 2026-06-12 00:57:04.731 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:__init__:626 - BaseVLLMInferenceEngine: set VLLM_ENABLE_V1_MULTIPROCESSING=0 [repeated 47x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) 2026-06-12 00:57:04.731 | WARNING | skyrl_train.inference_engines.vllm.vllm_engine:_create_engine:1192 - OpenAI API sampling params overridden: temperature=1.0, top_p=1.0, top_k=-1 [repeated 47x across cluster]
(AsyncVLLMInferenceEngine pid=379731, ip=10.128.25.25) 2026-06-12 00:57:04.700 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:_create_engine:1244 - Engine startup stagger: sleeping 1.80s (attempt 1/5) to avoid port collisions [repeated 47x across cluster]
(skyrl_entrypoint pid=364638) 2026-06-12 00:57:08.981 | INFO  | skyrl_train.workers.worker:_initiate_actors:636 - Initializing process group for RayActorGroup
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) [W612 00:57:09.772933846 socket.cpp:767] [c10d] The client socket cannot be initialized to connect to [jpbo-029-44.jupiter.internal]:44913 (errno: 97 - Address family not supported by protocol).
(raylet, ip=10.128.25.172) 2026-06-12 00:57:09,981 WARNING node.py:1846 -- The object spilling config is specified from an unstable API - system config or environment variable. This is subject to change in the future. You can use the stable API - --object-spilling-directory in ray start or object_spilling_directory in ray.init() to specify the object spilling directory instead. If you need more advanced settings, please open a github issue with the Ray team.
(pid=364947) Using blocking ray.get inside async actor. This blocks the event loop. Please use `await` on object ref with asyncio.gather if you want to yield execution to the event loop instead.
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored. [repeated 6x across cluster]
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) The tokenizer you are loading from '/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue. [repeated 3x across cluster]
(raylet) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/vllm/__init__.py:7: RuntimeWarning: Failed to read commit hash: [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) No module named 'vllm._version' [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) from .version import __version__, __version_tuple__ # isort:skip [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) (EngineCore_DP0 pid=443505) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/torch/__init__.py:1617: UserWarning: Please use the new API settings to control TF32 behavior, such as torch.backends.cudnn.conv.fp32_precision = 'tf32' or torch.backends.cuda.matmul.fp32_precision = 'ieee'. Old settings, e.g, torch.backends.cuda.matmul.allow_tf32 = True, torch.backends.cudnn.allow_tf32 = True, allowTF32CuDNN() and allowTF32CuBLAS() will be deprecated after Pytorch 2.9. Please see https://pytorch.org/docs/main/notes/cuda.html#tensorfloat-32-tf32-on-ampere-and-later-devices (Triggered internally at /pytorch/aten/src/ATen/Context.cpp:80.)
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) (EngineCore_DP0 pid=443505) _C._set_float32_matmul_precision(precision)
(raylet) 2026-06-12 00:57:10,083 WARNING node.py:1846 -- The object spilling config is specified from an unstable API - system config or environment variable. This is subject to change in the future. You can use the stable API - --object-spilling-directory in ray start or object_spilling_directory in ray.init() to specify the object spilling directory instead. If you need more advanced settings, please open a github issue with the Ray team. [repeated 6x across cluster]
(pid=441955, ip=10.128.25.172) Using blocking ray.get inside async actor. This blocks the event loop. Please use `await` on object ref with asyncio.gather if you want to yield execution to the event loop instead. [repeated 6x across cluster]
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) (EngineCore_DP0 pid=443494) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) (EngineCore_DP0 pid=443488) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) [W612 00:57:27.377459927 socket.cpp:767] [c10d] The client socket cannot be initialized to connect to [jpbo-029-46-interconnect-1.jupiter.internal]:47029 (errno: 97 - Address family not supported by protocol).
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) [W612 00:57:27.379402447 Utils.hpp:166] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator())
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) [rank0]:[W612 00:57:27.384365575 Utils.hpp:137] Warning: Environment variable TORCH_NCCL_TRACE_BUFFER_SIZE is deprecated; use TORCH_FR_BUFFER_SIZE instead (function operator())
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) (EngineCore_DP0 pid=443484) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) (EngineCore_DP0 pid=443488)
Loading safetensors checkpoint shards: 0% Completed | 0/4 [00:00<?, ?it/s]
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) (EngineCore_DP0 pid=443488)
Loading safetensors checkpoint shards: 25% Completed | 1/4 [00:04<00:13, 4.60s/it]
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) (EngineCore_DP0 pid=443484) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/torch/__init__.py:1617: UserWarning: Please use the new API settings to control TF32 behavior, such as torch.backends.cudnn.conv.fp32_precision = 'tf32' or torch.backends.cuda.matmul.fp32_precision = 'ieee'. Old settings, e.g, torch.backends.cuda.matmul.allow_tf32 = True, torch.backends.cudnn.allow_tf32 = True, allowTF32CuDNN() and allowTF32CuBLAS() will be deprecated after Pytorch 2.9. Please see https://pytorch.org/docs/main/notes/cuda.html#tensorfloat-32-tf32-on-ampere-and-later-devices (Triggered internally at /pytorch/aten/src/ATen/Context.cpp:80.) [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) [W612 00:57:27.641765305 socket.cpp:767] [c10d] The client socket cannot be initialized to connect to [jpbo-029-46-interconnect-1.jupiter.internal]:56675 (errno: 97 - Address family not supported by protocol). [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) [W612 00:57:27.642268302 Utils.hpp:166] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) [rank0]:[W612 00:57:27.644246917 Utils.hpp:137] Warning: Environment variable TORCH_NCCL_TRACE_BUFFER_SIZE is deprecated; use TORCH_FR_BUFFER_SIZE instead (function operator()) [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) (EngineCore_DP0 pid=443484)
Loading safetensors checkpoint shards: 0% Completed | 0/4 [00:00<?, ?it/s] [repeated 3x across cluster]
(pid=441953, ip=10.128.25.172) [2026-06-12 00:57:39,999 E 441953 442066] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) (EngineCore_DP0 pid=443494)
Loading safetensors checkpoint shards: 50% Completed | 2/4 [00:08<00:08, 4.33s/it] [repeated 7x across cluster]
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) (EngineCore_DP0 pid=443488)
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) (EngineCore_DP0 pid=443505)
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) (EngineCore_DP0 pid=443484)
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) (EngineCore_DP0 pid=443494)
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) (EngineCore_DP0 pid=443488) The tokenizer you are loading from '/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
(pid=364945) [2026-06-12 00:57:40,202 E 364945 365175] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14 [repeated 6x across cluster]
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) (EngineCore_DP0 pid=443494)
Loading safetensors checkpoint shards: 100% Completed | 4/4 [00:14<00:00, 3.57s/it] [repeated 12x across cluster]
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) 2026-06-12 00:57:49.377 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:_create_engine:1301 - Initializing OpenAIServingChat with custom_chat_template read from: chat_templates/qwen3_thinking_acc.jinja2
(AsyncVLLMInferenceEngine pid=326155, ip=10.128.25.27) The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored.
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) (EngineCore_DP0 pid=443494) The tokenizer you are loading from '/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue. [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) 2026-06-12 00:57:49.406 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:_create_engine:1301 - Initializing OpenAIServingChat with custom_chat_template read from: chat_templates/qwen3_thinking_acc.jinja2 [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=305427, ip=10.128.25.164) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e
(AsyncVLLMInferenceEngine pid=305427, ip=10.128.25.164) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e
(AsyncVLLMInferenceEngine pid=316510, ip=10.128.25.28) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/vllm/__init__.py:7: RuntimeWarning: Failed to read commit hash:
(AsyncVLLMInferenceEngine pid=316510, ip=10.128.25.28) No module named 'vllm._version'
(AsyncVLLMInferenceEngine pid=316510, ip=10.128.25.28) from .version import __version__, __version_tuple__ # isort:skip
(FSDPPolicyWorkerBase pid=364947) [W612 01:01:03.253829049 socket.cpp:767] [c10d] The client socket cannot be initialized to connect to [jpbo-029-44.jupiter.internal]:44913 (errno: 97 - Address family not supported by protocol).
(FSDPPolicyWorkerBase pid=364947) [W612 01:01:03.254567369 Utils.hpp:166] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator())
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored. [repeated 87x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) The tokenizer you are loading from '/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue. [repeated 44x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 86x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/vllm/__init__.py:7: RuntimeWarning: Failed to read commit hash: [repeated 43x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) No module named 'vllm._version' [repeated 43x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) from .version import __version__, __version_tuple__ # isort:skip [repeated 43x across cluster]
(skyrl_entrypoint pid=364638) 2026-06-12 01:01:06.020 | INFO  | skyrl_train.workers.worker:_initiate_actors:638 - Initialized process group for RayActorGroup
(skyrl_entrypoint pid=364638) 2026-06-12 01:01:06.030 | INFO  | skyrl_train.workers.worker:_initiate_actors:640 - Mesh Ranks: [MeshRank(dp=0, sp=0, tp=0, pp=0, world_size=8, dp_size=8, pp_size=1), MeshRank(dp=1, sp=0, tp=0, pp=0, world_size=8, dp_size=8, pp_size=1), MeshRank(dp=2, sp=0, tp=0, pp=0, world_size=8, dp_size=8, pp_size=1), MeshRank(dp=3, sp=0, tp=0, pp=0, world_size=8, dp_size=8, pp_size=1), MeshRank(dp=4, sp=0, tp=0, pp=0, world_size=8, dp_size=8, pp_size=1), MeshRank(dp=5, sp=0, tp=0, pp=0, world_size=8, dp_size=8, pp_size=1), MeshRank(dp=6, sp=0, tp=0, pp=0, world_size=8, dp_size=8, pp_size=1), MeshRank(dp=7, sp=0, tp=0, pp=0, world_size=8, dp_size=8, pp_size=1)]
(FSDPPolicyWorkerBase pid=364947) `torch_dtype` is deprecated! Use `dtype` instead!
(FSDPPolicyWorkerBase pid=364947)
Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172)
Loading checkpoint shards: 25%|██▌ | 1/4 [00:01<00:03, 1.22s/it]
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) [W612 01:01:05.915738414 socket.cpp:767] [c10d] The client socket cannot be initialized to connect to [jpbo-029-44-interconnect-1.jupiter.internal]:44913 (errno: 97 - Address family not supported by protocol). [repeated 6x across cluster]
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) [W612 01:01:05.005877978 Utils.hpp:166] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [repeated 7x across cluster]
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) `torch_dtype` is deprecated! Use `dtype` instead! [repeated 7x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172)
Loading checkpoint shards: 75%|███████▌ | 3/4 [00:04<00:01, 1.64s/it]
Loading checkpoint shards: 100%|██████████| 4/4 [00:04<00:00, 1.21s/it]
(FSDPPolicyWorkerBase pid=364947)
Loading checkpoint shards: 100%|██████████| 4/4 [00:04<00:00, 1.22s/it]
(AsyncVLLMInferenceEngine pid=349371, ip=10.128.25.161) (EngineCore_DP0 pid=349999) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/torch/__init__.py:1617: UserWarning: Please use the new API settings to control TF32 behavior, such as torch.backends.cudnn.conv.fp32_precision = 'tf32' or torch.backends.cuda.matmul.fp32_precision = 'ieee'. Old settings, e.g, torch.backends.cuda.matmul.allow_tf32 = True, torch.backends.cudnn.allow_tf32 = True, allowTF32CuDNN() and allowTF32CuBLAS() will be deprecated after Pytorch 2.9. Please see https://pytorch.org/docs/main/notes/cuda.html#tensorfloat-32-tf32-on-ampere-and-later-devices (Triggered internally at /pytorch/aten/src/ATen/Context.cpp:80.)
(AsyncVLLMInferenceEngine pid=349371, ip=10.128.25.161) (EngineCore_DP0 pid=349999) _C._set_float32_matmul_precision(precision)
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172)
Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s] [repeated 7x across cluster]
(FSDPPolicyWorkerBase pid=364945)
Loading checkpoint shards: 75%|███████▌ | 3/4 [00:04<00:01, 1.66s/it] [repeated 19x across cluster]
(AsyncVLLMInferenceEngine pid=349498, ip=10.128.25.161) (EngineCore_DP0 pid=349991) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=478789, ip=10.128.25.176) (EngineCore_DP0 pid=479189) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=478790, ip=10.128.25.176) (EngineCore_DP0 pid=479185) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=326287, ip=10.128.25.27) (EngineCore_DP0 pid=326760) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) (EngineCore_DP0 pid=326772) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=316510, ip=10.128.25.28) (EngineCore_DP0 pid=317118) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=316638, ip=10.128.25.28) (EngineCore_DP0 pid=317128) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=316639, ip=10.128.25.28) (EngineCore_DP0 pid=317124) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=349499, ip=10.128.25.161) (EngineCore_DP0 pid=350003) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=316064, ip=10.128.25.23) (EngineCore_DP0 pid=316471) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) (EngineCore_DP0 pid=316475) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=478791, ip=10.128.25.176) (EngineCore_DP0 pid=479193) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) (EngineCore_DP0 pid=301668) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=301250, ip=10.128.25.163) (EngineCore_DP0 pid=301661) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=301252, ip=10.128.25.163) (EngineCore_DP0 pid=301664) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=326155, ip=10.128.25.27) (EngineCore_DP0 pid=326770) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=315936, ip=10.128.25.23) (EngineCore_DP0 pid=316481) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=316510, ip=10.128.25.28) [W612 01:01:16.718846230 socket.cpp:767] [c10d] The client socket cannot be initialized to connect to [jpbo-026-44-interconnect-1.jupiter.internal]:51703 (errno: 97 - Address family not supported by protocol).
(AsyncVLLMInferenceEngine pid=316510, ip=10.128.25.28) [W612 01:01:16.719483719 Utils.hpp:166] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator())
(AsyncVLLMInferenceEngine pid=349371, ip=10.128.25.161) [rank0]:[W612 01:01:16.888041039 Utils.hpp:137] Warning: Environment variable TORCH_NCCL_TRACE_BUFFER_SIZE is deprecated; use TORCH_FR_BUFFER_SIZE instead (function operator())
(AsyncVLLMInferenceEngine pid=478659, ip=10.128.25.176) (EngineCore_DP0 pid=479197) _C._set_float32_matmul_precision(precision)
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172)
Loading checkpoint shards: 75%|███████▌ | 3/4 [00:04<00:01, 1.65s/it]
Loading checkpoint shards: 100%|██████████| 4/4 [00:04<00:00, 1.21s/it] [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=301251, ip=10.128.25.163) (EngineCore_DP0 pid=301662) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=316640, ip=10.128.25.28) (EngineCore_DP0 pid=317120) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=349500, ip=10.128.25.161) (EngineCore_DP0 pid=349997) _C._set_float32_matmul_precision(precision)
(FSDPPolicyWorkerBase pid=364945)
Loading checkpoint shards: 100%|██████████| 4/4 [00:04<00:00, 1.22s/it] [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=326288, ip=10.128.25.27) (EngineCore_DP0 pid=326764) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=316063, ip=10.128.25.23) (EngineCore_DP0 pid=316483) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=349498, ip=10.128.25.161) (EngineCore_DP0 pid=349991)
Loading safetensors checkpoint shards: 0% Completed | 0/4 [00:00<?, ?it/s]
(AsyncVLLMInferenceEngine pid=379729, ip=10.128.25.25) (EngineCore_DP0 pid=380138) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=379730, ip=10.128.25.25) (EngineCore_DP0 pid=380139) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=305427, ip=10.128.25.164) (EngineCore_DP0 pid=305964) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=305556, ip=10.128.25.164) (EngineCore_DP0 pid=305976) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=305555, ip=10.128.25.164) (EngineCore_DP0 pid=305972) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=300569, ip=10.128.25.162) (EngineCore_DP0 pid=301120) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=300697, ip=10.128.25.162) (EngineCore_DP0 pid=301112) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=249097, ip=10.128.25.24) (EngineCore_DP0 pid=249632) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=249227, ip=10.128.25.24) (EngineCore_DP0 pid=249633) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=249225, ip=10.128.25.24) (EngineCore_DP0 pid=249625) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) (EngineCore_DP0 pid=380145) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=300699, ip=10.128.25.162) (EngineCore_DP0 pid=301118) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=305554, ip=10.128.25.164) (EngineCore_DP0 pid=305968) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) (EngineCore_DP0 pid=249637) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=379731, ip=10.128.25.25) (EngineCore_DP0 pid=380144) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=300698, ip=10.128.25.162) (EngineCore_DP0 pid=301108) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=300698, ip=10.128.25.162) (EngineCore_DP0 pid=301108) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/torch/__init__.py:1617: UserWarning: Please use the new API settings to control TF32 behavior, such as torch.backends.cudnn.conv.fp32_precision = 'tf32' or torch.backends.cuda.matmul.fp32_precision = 'ieee'. Old settings, e.g, torch.backends.cuda.matmul.allow_tf32 = True, torch.backends.cudnn.allow_tf32 = True, allowTF32CuDNN() and allowTF32CuBLAS() will be deprecated after Pytorch 2.9. Please see https://pytorch.org/docs/main/notes/cuda.html#tensorfloat-32-tf32-on-ampere-and-later-devices (Triggered internally at /pytorch/aten/src/ATen/Context.cpp:80.) [repeated 39x across cluster]
(AsyncVLLMInferenceEngine pid=478659, ip=10.128.25.176) (EngineCore_DP0 pid=479197)
Loading safetensors checkpoint shards: 25% Completed | 1/4 [00:03<00:10, 3.44s/it]
(AsyncVLLMInferenceEngine pid=300698, ip=10.128.25.162) [W612 01:01:19.363117061 socket.cpp:767] [c10d] The client socket cannot be initialized to connect to [jpbo-029-34-interconnect-1.jupiter.internal]:35647 (errno: 97 - Address family not supported by protocol). [repeated 39x across cluster]
(AsyncVLLMInferenceEngine pid=300698, ip=10.128.25.162) [W612 01:01:19.363562812 Utils.hpp:166] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [repeated 39x across cluster]
(AsyncVLLMInferenceEngine pid=300698, ip=10.128.25.162) [rank0]:[W612 01:01:19.365486709 Utils.hpp:137] Warning: Environment variable TORCH_NCCL_TRACE_BUFFER_SIZE is deprecated; use TORCH_FR_BUFFER_SIZE instead (function operator()) [repeated 39x across cluster]
(AsyncVLLMInferenceEngine pid=300699, ip=10.128.25.162) (EngineCore_DP0 pid=301118)
Loading safetensors checkpoint shards: 0% Completed | 0/4 [00:00<?, ?it/s] [repeated 39x across cluster]
(AsyncVLLMInferenceEngine pid=349371, ip=10.128.25.161) (EngineCore_DP0 pid=349999)
Loading safetensors checkpoint shards: 50% Completed | 2/4 [00:08<00:08, 4.23s/it] [repeated 60x across cluster]
(AsyncVLLMInferenceEngine pid=478659, ip=10.128.25.176) (EngineCore_DP0 pid=479197)
(AsyncVLLMInferenceEngine pid=478659, ip=10.128.25.176) (EngineCore_DP0 pid=479197)
Loading safetensors checkpoint shards: 100% Completed | 4/4 [00:14<00:00, 3.51s/it] [repeated 41x across cluster]
(AsyncVLLMInferenceEngine pid=478789, ip=10.128.25.176) (EngineCore_DP0 pid=479189)
(AsyncVLLMInferenceEngine pid=478791, ip=10.128.25.176) (EngineCore_DP0 pid=479193)
(AsyncVLLMInferenceEngine pid=478790, ip=10.128.25.176) (EngineCore_DP0 pid=479185)
(AsyncVLLMInferenceEngine pid=316510, ip=10.128.25.28) (EngineCore_DP0 pid=317118)
(AsyncVLLMInferenceEngine pid=316638, ip=10.128.25.28) (EngineCore_DP0 pid=317128)
(AsyncVLLMInferenceEngine pid=316640, ip=10.128.25.28) (EngineCore_DP0 pid=317120)
(AsyncVLLMInferenceEngine pid=316639, ip=10.128.25.28) (EngineCore_DP0 pid=317124)
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) (EngineCore_DP0 pid=301668)
(AsyncVLLMInferenceEngine pid=301250, ip=10.128.25.163) (EngineCore_DP0 pid=301661)
(AsyncVLLMInferenceEngine pid=301251, ip=10.128.25.163) (EngineCore_DP0 pid=301662)
(AsyncVLLMInferenceEngine pid=301252, ip=10.128.25.163) (EngineCore_DP0 pid=301664)
(AsyncVLLMInferenceEngine pid=315936, ip=10.128.25.23) (EngineCore_DP0 pid=316481)
(AsyncVLLMInferenceEngine pid=316064, ip=10.128.25.23) (EngineCore_DP0 pid=316471)
(AsyncVLLMInferenceEngine pid=316063, ip=10.128.25.23) (EngineCore_DP0 pid=316483)
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) (EngineCore_DP0 pid=316475)
(AsyncVLLMInferenceEngine pid=326155, ip=10.128.25.27) (EngineCore_DP0 pid=326770)
(AsyncVLLMInferenceEngine pid=326288, ip=10.128.25.27) (EngineCore_DP0 pid=326764)
(AsyncVLLMInferenceEngine pid=326287, ip=10.128.25.27) (EngineCore_DP0 pid=326760)
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) (EngineCore_DP0 pid=326772)
(AsyncVLLMInferenceEngine pid=349371, ip=10.128.25.161) (EngineCore_DP0 pid=349999)
(AsyncVLLMInferenceEngine pid=349499, ip=10.128.25.161) (EngineCore_DP0 pid=350003)
(AsyncVLLMInferenceEngine pid=349500, ip=10.128.25.161) (EngineCore_DP0 pid=349997)
(AsyncVLLMInferenceEngine pid=349498, ip=10.128.25.161) (EngineCore_DP0 pid=349991)
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) (EngineCore_DP0 pid=380145)
(AsyncVLLMInferenceEngine pid=379729, ip=10.128.25.25) (EngineCore_DP0 pid=380138)
(AsyncVLLMInferenceEngine pid=379730, ip=10.128.25.25) (EngineCore_DP0 pid=380139)
(AsyncVLLMInferenceEngine pid=379731, ip=10.128.25.25) (EngineCore_DP0 pid=380144)
(AsyncVLLMInferenceEngine pid=300569, ip=10.128.25.162) (EngineCore_DP0 pid=301120)
(AsyncVLLMInferenceEngine pid=300698, ip=10.128.25.162) (EngineCore_DP0 pid=301108)
(AsyncVLLMInferenceEngine pid=300697, ip=10.128.25.162) (EngineCore_DP0 pid=301112)
(AsyncVLLMInferenceEngine pid=300699, ip=10.128.25.162) (EngineCore_DP0 pid=301118)
(AsyncVLLMInferenceEngine pid=249097, ip=10.128.25.24) (EngineCore_DP0 pid=249632)
(AsyncVLLMInferenceEngine pid=249227, ip=10.128.25.24) (EngineCore_DP0 pid=249633)
(AsyncVLLMInferenceEngine pid=249225, ip=10.128.25.24) (EngineCore_DP0 pid=249625)
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) (EngineCore_DP0 pid=249637)
(AsyncVLLMInferenceEngine pid=305427, ip=10.128.25.164) (EngineCore_DP0 pid=305964)
(AsyncVLLMInferenceEngine pid=305554, ip=10.128.25.164) (EngineCore_DP0 pid=305968)
(AsyncVLLMInferenceEngine pid=305556, ip=10.128.25.164) (EngineCore_DP0 pid=305976)
(AsyncVLLMInferenceEngine pid=305555, ip=10.128.25.164) (EngineCore_DP0 pid=305972)
(FSDPPolicyWorkerBase pid=364947) [rank5]:[W612 01:01:35.443417320 Utils.hpp:137] Warning: Environment variable TORCH_NCCL_TRACE_BUFFER_SIZE is deprecated; use TORCH_FR_BUFFER_SIZE instead (function operator())
(AsyncVLLMInferenceEngine pid=316064, ip=10.128.25.23) (EngineCore_DP0 pid=316471) The tokenizer you are loading from '/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) 2026-06-12 01:01:37.057 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:_create_engine:1301 - Initializing OpenAIServingChat with custom_chat_template read from: chat_templates/qwen3_thinking_acc.jinja2
(AsyncVLLMInferenceEngine pid=305555, ip=10.128.25.164) (EngineCore_DP0 pid=305972)
Loading safetensors checkpoint shards: 100% Completed | 4/4 [00:15<00:00, 3.78s/it] [repeated 98x across cluster]
(skyrl_entrypoint pid=364638) 2026-06-12 01:01:38.211 | INFO  | skyrl_train.trainer:build_models:851 - init policy/ref/critic models done
(skyrl_entrypoint pid=364638) 2026-06-12 01:01:38.216 | INFO  | skyrl_train.fully_async_trainer:_maybe_enable_rollout_fanout:456 - Rollout fan-out ENABLED: replacing single-process generator with RolloutDispatcher (K=4, cpus_per_coordinator=8).
(skyrl_entrypoint pid=364638) 2026-06-12 01:01:38.239 | INFO  | examples.terminal_bench.rollout_coordinator:__init__:387 - [RolloutDispatcher] fan-out path: overriding inference host 127.0.0.1 -> 10.128.25.17 (routable head IP) for coordinator litellm base_url connectivity
(skyrl_entrypoint pid=364638) 2026-06-12 01:01:38.239 | INFO  | examples.terminal_bench.rollout_coordinator:__init__:405 - [RolloutDispatcher] configured num_coordinators=4, cpus_per_coordinator=8
(skyrl_entrypoint pid=364638) 2026-06-12 01:01:38.264 | INFO  | examples.terminal_bench.rollout_coordinator:startup:434 - [RolloutDispatcher] PlacementGroup ready: 4 bundles x 8 CPU (SPREAD)
(raylet, ip=10.128.25.161) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e
(raylet, ip=10.128.25.161) 2026-06-12 01:01:39,065 WARNING node.py:1846 -- The object spilling config is specified from an unstable API - system config or environment variable. This is subject to change in the future. You can use the stable API - --object-spilling-directory in ray start or object_spilling_directory in ray.init() to specify the object spilling directory instead. If you need more advanced settings, please open a github issue with the Ray team.
(RolloutCoordinator pid=350242, ip=10.128.25.161) 2026-06-12 01:01:44.319 | INFO | examples.terminal_bench.rollout_coordinator:_scale_terminal_bench_cfg:121 - [RolloutCoordinator] scaled n_concurrent_trials 675 -> 168 (// 4)
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) [rank2]:[W612 01:01:35.573353744 Utils.hpp:137] Warning: Environment variable TORCH_NCCL_TRACE_BUFFER_SIZE is deprecated; use TORCH_FR_BUFFER_SIZE instead (function operator()) [repeated 7x across cluster]
(AsyncVLLMInferenceEngine pid=305427, ip=10.128.25.164) (EngineCore_DP0 pid=305964) The tokenizer you are loading from '/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue. [repeated 39x across cluster]
(AsyncVLLMInferenceEngine pid=305554, ip=10.128.25.164) 2026-06-12 01:01:39.969 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:_create_engine:1301 - Initializing OpenAIServingChat with custom_chat_template read from: chat_templates/qwen3_thinking_acc.jinja2 [repeated 39x across cluster]
(raylet, ip=10.128.25.161) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 5x across cluster]
(skyrl_entrypoint pid=364638) 2026-06-12 01:01:44.531 | INFO  | examples.terminal_bench.rollout_coordinator:startup:469 - [RolloutDispatcher] coordinator 1/4 started
(RolloutCoordinator pid=350242, ip=10.128.25.161) 2026-06-12 01:01:44.526 | INFO | examples.terminal_bench.terminal_bench_generator:_configure_harbor_logging:242 - Harbor logging level set to INFO
(RolloutCoordinator pid=350242, ip=10.128.25.161) 2026-06-12 01:01:44.526 | INFO | examples.terminal_bench.terminal_bench_generator:__init__:142 - TerminalBenchGenerator initialized with HarborConfigBuilder. Exposed fields: ['name', 'max_episodes', 'enable_summarize', 'store_all_messages', 'trajectory_config', 'enable_episode_logging', 'record_terminal_session', 'enable_pane_logging', 'strict_json_parser', 'interleaved_thinking', 'extra_body', 'override_timeout_sec', 'override_cpus', 'override_memory_mb', 'override_storage_mb', 'auto_snapshot', 'verifier_override_timeout_sec', 'max_retries', 'min_wait_sec', 'max_wait_sec', 'wait_multiplier', 'exclude_exceptions', 'n_concurrent_trials', 'log_level', 'enable_reward_shaping', 'collect_rollout_details', 'enable_error_classification', 'mask_exceptions', 'default_error_treatment', 'passthrough_exceptions', 'zero_exceptions']. Retry config: max_retries=3, backoff=60.0-600.0s. Concurrent trials: 168. Reward shaping: enabled=False, shaper=pass_ratio. Error classification: enabled=True
(RolloutCoordinator pid=350242, ip=10.128.25.161) 2026-06-12 01:01:44.526 | INFO | examples.terminal_bench.terminal_bench_generator:__init__:158 - TerminalBenchGenerator initialized with custom chat template read from: chat_templates/qwen3_thinking_acc.jinja2
(RolloutCoordinator pid=350242, ip=10.128.25.161) 2026-06-12 01:01:44.527 | INFO | examples.terminal_bench.rollout_coordinator:__init__:246 - [RolloutCoordinator 0/4] constructed (http=10.128.25.17:8000)
(RolloutCoordinator pid=350242, ip=10.128.25.161) 2026-06-12 01:01:44.530 | INFO | examples.terminal_bench.terminal_bench_generator:_create_orchestrator:298 - QueueOrchestrator created and started with n_concurrent_trials=168, rollback_hook registered for ContextLengthExceededError/AgentTimeoutError
(RolloutCoordinator pid=350242, ip=10.128.25.161) 2026-06-12 01:01:44.530 | INFO | examples.terminal_bench.terminal_bench_generator:startup:255 - TerminalBenchGenerator startup complete. Shared orchestrator ready with n_concurrent_trials=168
(RolloutCoordinator pid=350242, ip=10.128.25.161) 2026-06-12 01:01:44.530 | INFO | examples.terminal_bench.rollout_coordinator:startup:254 - [RolloutCoordinator 0] startup complete
(raylet, ip=10.128.25.176) 2026-06-12 01:01:47,209 WARNING node.py:1846 -- The object spilling config is specified from an unstable API - system config or environment variable. This is subject to change in the future. You can use the stable API - --object-spilling-directory in ray start or object_spilling_directory in ray.init() to specify the object spilling directory instead. If you need more advanced settings, please open a github issue with the Ray team.
(RolloutCoordinator pid=479438, ip=10.128.25.176) 2026-06-12 01:01:51.275 | INFO | examples.terminal_bench.rollout_coordinator:_scale_terminal_bench_cfg:121 - [RolloutCoordinator] scaled n_concurrent_trials 675 -> 168 (// 4)
(RolloutCoordinator pid=350242, ip=10.128.25.161) The tokenizer you are loading from '/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
(raylet, ip=10.128.25.176) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 6x across cluster]
(skyrl_entrypoint pid=364638) 2026-06-12 01:01:51.491 | INFO  | examples.terminal_bench.rollout_coordinator:startup:469 - [RolloutDispatcher] coordinator 2/4 started
(RolloutCoordinator pid=479438, ip=10.128.25.176) The tokenizer you are loading from '/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
(RolloutCoordinator pid=479438, ip=10.128.25.176) 2026-06-12 01:01:51.487 | INFO | examples.terminal_bench.terminal_bench_generator:_configure_harbor_logging:242 - Harbor logging level set to INFO
(RolloutCoordinator pid=479438, ip=10.128.25.176) 2026-06-12 01:01:51.487 | INFO | examples.terminal_bench.terminal_bench_generator:__init__:142 - TerminalBenchGenerator initialized with HarborConfigBuilder. Exposed fields: ['name', 'max_episodes', 'enable_summarize', 'store_all_messages', 'trajectory_config', 'enable_episode_logging', 'record_terminal_session', 'enable_pane_logging', 'strict_json_parser', 'interleaved_thinking', 'extra_body', 'override_timeout_sec', 'override_cpus', 'override_memory_mb', 'override_storage_mb', 'auto_snapshot', 'verifier_override_timeout_sec', 'max_retries', 'min_wait_sec', 'max_wait_sec', 'wait_multiplier', 'exclude_exceptions', 'n_concurrent_trials', 'log_level', 'enable_reward_shaping', 'collect_rollout_details', 'enable_error_classification', 'mask_exceptions', 'default_error_treatment', 'passthrough_exceptions', 'zero_exceptions']. Retry config: max_retries=3, backoff=60.0-600.0s. Concurrent trials: 168. Reward shaping: enabled=False, shaper=pass_ratio. Error classification: enabled=True
(RolloutCoordinator pid=479438, ip=10.128.25.176) 2026-06-12 01:01:51.487 | INFO | examples.terminal_bench.terminal_bench_generator:__init__:158 - TerminalBenchGenerator initialized with custom chat template read from: chat_templates/qwen3_thinking_acc.jinja2
(RolloutCoordinator pid=479438, ip=10.128.25.176) 2026-06-12 01:01:51.487 | INFO | examples.terminal_bench.rollout_coordinator:__init__:246 - [RolloutCoordinator 1/4] constructed (http=10.128.25.17:8000)
(RolloutCoordinator pid=479438, ip=10.128.25.176) 2026-06-12 01:01:51.490 | INFO | examples.terminal_bench.terminal_bench_generator:_create_orchestrator:298 - QueueOrchestrator created and started with n_concurrent_trials=168, rollback_hook registered for ContextLengthExceededError/AgentTimeoutError
(RolloutCoordinator pid=479438, ip=10.128.25.176) 2026-06-12 01:01:51.490 | INFO | examples.terminal_bench.terminal_bench_generator:startup:255 - TerminalBenchGenerator startup complete. Shared orchestrator ready with n_concurrent_trials=168
(RolloutCoordinator pid=479438, ip=10.128.25.176) 2026-06-12 01:01:51.490 | INFO | examples.terminal_bench.rollout_coordinator:startup:254 - [RolloutCoordinator 1] startup complete
(raylet, ip=10.128.25.162) 2026-06-12 01:01:54,176 WARNING node.py:1846 -- The object spilling config is specified from an unstable API - system config or environment variable. This is subject to change in the future. You can use the stable API - --object-spilling-directory in ray start or object_spilling_directory in ray.init() to specify the object spilling directory instead. If you need more advanced settings, please open a github issue with the Ray team.
(RolloutCoordinator pid=301361, ip=10.128.25.162) 2026-06-12 01:01:58.518 | INFO | examples.terminal_bench.rollout_coordinator:_scale_terminal_bench_cfg:121 - [RolloutCoordinator] scaled n_concurrent_trials 675 -> 168 (// 4)
(raylet, ip=10.128.25.162) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 6x across cluster]
(RolloutCoordinator pid=301361, ip=10.128.25.162) The tokenizer you are loading from '/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
(RolloutCoordinator pid=301361, ip=10.128.25.162) 2026-06-12 01:01:58.740 | INFO | examples.terminal_bench.terminal_bench_generator:_configure_harbor_logging:242 - Harbor logging level set to INFO
(RolloutCoordinator pid=301361, ip=10.128.25.162) 2026-06-12 01:01:58.740 | INFO | examples.terminal_bench.terminal_bench_generator:__init__:142 - TerminalBenchGenerator initialized with HarborConfigBuilder. Exposed fields: ['name', 'max_episodes', 'enable_summarize', 'store_all_messages', 'trajectory_config', 'enable_episode_logging', 'record_terminal_session', 'enable_pane_logging', 'strict_json_parser', 'interleaved_thinking', 'extra_body', 'override_timeout_sec', 'override_cpus', 'override_memory_mb', 'override_storage_mb', 'auto_snapshot', 'verifier_override_timeout_sec', 'max_retries', 'min_wait_sec', 'max_wait_sec', 'wait_multiplier', 'exclude_exceptions', 'n_concurrent_trials', 'log_level', 'enable_reward_shaping', 'collect_rollout_details', 'enable_error_classification', 'mask_exceptions', 'default_error_treatment', 'passthrough_exceptions', 'zero_exceptions']. Retry config: max_retries=3, backoff=60.0-600.0s. Concurrent trials: 168. Reward shaping: enabled=False, shaper=pass_ratio. Error classification: enabled=True
(RolloutCoordinator pid=301361, ip=10.128.25.162) 2026-06-12 01:01:58.740 | INFO | examples.terminal_bench.terminal_bench_generator:__init__:158 - TerminalBenchGenerator initialized with custom chat template read from: chat_templates/qwen3_thinking_acc.jinja2
(RolloutCoordinator pid=301361, ip=10.128.25.162) 2026-06-12 01:01:58.740 | INFO | examples.terminal_bench.rollout_coordinator:__init__:246 - [RolloutCoordinator 2/4] constructed (http=10.128.25.17:8000)
(RolloutCoordinator pid=301361, ip=10.128.25.162) 2026-06-12 01:01:58.743 | INFO | examples.terminal_bench.terminal_bench_generator:_create_orchestrator:298 - QueueOrchestrator created and started with n_concurrent_trials=168, rollback_hook registered for ContextLengthExceededError/AgentTimeoutError
(RolloutCoordinator pid=301361, ip=10.128.25.162) 2026-06-12 01:01:58.743 | INFO | examples.terminal_bench.terminal_bench_generator:startup:255 - TerminalBenchGenerator startup complete. Shared orchestrator ready with n_concurrent_trials=168
(RolloutCoordinator pid=301361, ip=10.128.25.162) 2026-06-12 01:01:58.743 | INFO | examples.terminal_bench.rollout_coordinator:startup:254 - [RolloutCoordinator 2] startup complete
(skyrl_entrypoint pid=364638) 2026-06-12 01:01:58.744 | INFO  | examples.terminal_bench.rollout_coordinator:startup:469 - [RolloutDispatcher] coordinator 3/4 started
(raylet, ip=10.128.25.25) 2026-06-12 01:02:01,691 WARNING node.py:1846 -- The object spilling config is specified from an unstable API - system config or environment variable. This is subject to change in the future. You can use the stable API - --object-spilling-directory in ray start or object_spilling_directory in ray.init() to specify the object spilling directory instead. If you need more advanced settings, please open a github issue with the Ray team.
(RolloutCoordinator pid=380389, ip=10.128.25.25) 2026-06-12 01:02:07.745 | INFO | examples.terminal_bench.rollout_coordinator:_scale_terminal_bench_cfg:121 - [RolloutCoordinator] scaled n_concurrent_trials 675 -> 168 (// 4)
(raylet, ip=10.128.25.25) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 6x across cluster]
(RolloutCoordinator pid=380389, ip=10.128.25.25) The tokenizer you are loading from '/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
(RolloutCoordinator pid=380389, ip=10.128.25.25) 2026-06-12 01:02:07.967 | INFO | examples.terminal_bench.terminal_bench_generator:_configure_harbor_logging:242 - Harbor logging level set to INFO
(RolloutCoordinator pid=380389, ip=10.128.25.25) 2026-06-12 01:02:07.967 | INFO | examples.terminal_bench.terminal_bench_generator:__init__:142 - TerminalBenchGenerator initialized with HarborConfigBuilder. Exposed fields: ['name', 'max_episodes', 'enable_summarize', 'store_all_messages', 'trajectory_config', 'enable_episode_logging', 'record_terminal_session', 'enable_pane_logging', 'strict_json_parser', 'interleaved_thinking', 'extra_body', 'override_timeout_sec', 'override_cpus', 'override_memory_mb', 'override_storage_mb', 'auto_snapshot', 'verifier_override_timeout_sec', 'max_retries', 'min_wait_sec', 'max_wait_sec', 'wait_multiplier', 'exclude_exceptions', 'n_concurrent_trials', 'log_level', 'enable_reward_shaping', 'collect_rollout_details', 'enable_error_classification', 'mask_exceptions', 'default_error_treatment', 'passthrough_exceptions', 'zero_exceptions']. Retry config: max_retries=3, backoff=60.0-600.0s. Concurrent trials: 168. Reward shaping: enabled=False, shaper=pass_ratio. Error classification: enabled=True
(RolloutCoordinator pid=380389, ip=10.128.25.25) 2026-06-12 01:02:07.967 | INFO | examples.terminal_bench.terminal_bench_generator:__init__:158 - TerminalBenchGenerator initialized with custom chat template read from: chat_templates/qwen3_thinking_acc.jinja2
(RolloutCoordinator pid=380389, ip=10.128.25.25) 2026-06-12 01:02:07.967 | INFO | examples.terminal_bench.rollout_coordinator:__init__:246 - [RolloutCoordinator 3/4] constructed (http=10.128.25.17:8000)
(RolloutCoordinator pid=380389, ip=10.128.25.25) 2026-06-12 01:02:07.970 | INFO | examples.terminal_bench.terminal_bench_generator:_create_orchestrator:298 - QueueOrchestrator created and started with n_concurrent_trials=168, rollback_hook registered for ContextLengthExceededError/AgentTimeoutError
(RolloutCoordinator pid=380389, ip=10.128.25.25) 2026-06-12 01:02:07.971 | INFO | examples.terminal_bench.terminal_bench_generator:startup:255 - TerminalBenchGenerator startup complete. Shared orchestrator ready with n_concurrent_trials=168
(RolloutCoordinator pid=380389, ip=10.128.25.25) 2026-06-12 01:02:07.971 | INFO | examples.terminal_bench.rollout_coordinator:startup:254 - [RolloutCoordinator 3] startup complete
(skyrl_entrypoint pid=364638) 2026-06-12 01:02:07.972 | INFO  | examples.terminal_bench.rollout_coordinator:startup:469 - [RolloutDispatcher] coordinator 4/4 started
(skyrl_entrypoint pid=364638) 2026-06-12 01:02:07.972 | INFO  | examples.terminal_bench.rollout_coordinator:startup:477 - [RolloutDispatcher] 4 coordinators started
(skyrl_entrypoint pid=364638) 2026-06-12 01:02:07.972 | INFO  | skyrl_train.fully_async_trainer:train:485 - Generator startup complete
(skyrl_entrypoint pid=364638) 2026-06-12 01:02:07.972 | INFO  | skyrl_train.fully_async_trainer:_train_loop:510 - Started: 'load_checkpoints'
(skyrl_entrypoint pid=364638) 2026-06-12 01:02:07.975 | INFO  | skyrl_train.trainer:load_checkpoints:1735 - Loading checkpoint from: /e/data1/datasets/playground/ot-baf/explore-tis-untrunc/explore-tis-untrunc/checkpoints/global_step_82
(skyrl_entrypoint pid=364638) 2026-06-12 01:02:07.975 | INFO  | skyrl_train.trainer:load_checkpoints:1741 - Resuming from global_step: 82
(skyrl_entrypoint pid=364638) 2026-06-12 01:02:07.981 | INFO  | skyrl_train.trainer:load_checkpoints:1757 - Successfully loaded trainer state
(skyrl_entrypoint pid=364638) 2026-06-12 01:02:07.983 | INFO  | skyrl_train.trainer:load_checkpoints:1767 - Successfully loaded dataloader state
(skyrl_entrypoint pid=364638) 2026-06-12 01:02:07.983 | INFO  | skyrl_train.trainer:load_checkpoints:1776 - Loading policy checkpoint from /e/data1/datasets/playground/ot-baf/explore-tis-untrunc/explore-tis-untrunc/checkpoints/global_step_82/policy
(RolloutCoordinator pid=350242, ip=10.128.25.161) [2026-06-12 01:02:09,083 E 350242 350282] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14
(RolloutCoordinator pid=479438, ip=10.128.25.176) [2026-06-12 01:02:17,227 E 479438 479478] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14
(RolloutCoordinator pid=301361, ip=10.128.25.162) [2026-06-12 01:02:24,194 E 301361 301401] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/torch/distributed/distributed_c10d.py:4876: UserWarning: barrier(): using the device under current context. You can specify `device_id` in `init_process_group` to mute this warning.
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) warnings.warn( # warn only once
(skyrl_entrypoint pid=364638) 2026-06-12 01:02:29.436 | INFO  | skyrl_train.trainer:load_checkpoints:1786 - Successfully loaded policy checkpoint
(skyrl_entrypoint pid=364638) 2026-06-12 01:02:29.436 | INFO  | skyrl_train.trainer:load_checkpoints:1802 - Successfully loaded complete checkpoint state from global_step_82
(skyrl_entrypoint pid=364638) 2026-06-12 01:02:29.436 | INFO  | skyrl_train.fully_async_trainer:_train_loop:512 - Resumed training from global_step 82
(skyrl_entrypoint pid=364638) 2026-06-12 01:02:29.436 | WARNING  | skyrl_train.fully_async_trainer:_train_loop:517 - No data consumption state found in checkpoint — resume may re-train on already-consumed data
(skyrl_entrypoint pid=364638) 2026-06-12 01:02:29.437 | WARNING  | skyrl_train.fully_async_trainer:_train_loop:537 - Data consumption count mismatch on resume: expected 256, got 0. This can happen after epoch boundary transitions or error recovery.
(skyrl_entrypoint pid=364638) 2026-06-12 01:02:29.437 | INFO  | skyrl_train.fully_async_trainer:_train_loop:510 - Finished: 'load_checkpoints', time cost: 21.47s
(skyrl_entrypoint pid=364638) 2026-06-12 01:02:29.437 | INFO  | skyrl_train.fully_async_trainer:_train_loop:544 - Started: 'init_weight_sync_state'
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/vllm/__init__.py:7: RuntimeWarning: Failed to read commit hash:
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) No module named 'vllm._version'
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) from .version import __version__, __version_tuple__ # isort:skip
(RolloutCoordinator pid=380389, ip=10.128.25.25) [2026-06-12 01:02:31,710 E 380389 380429] core_worker_process.cc:842: Failed to establish connection to the metrics exporter agent. Metrics will not be exported. Exporter agent status: RpcError: Running out of retries to initialize the metrics agent. rpc_code: 14
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) 2026-06-12 01:02:35.472 | INFO  | logging:info:2216 - [weight-sync] Using master_addr=10.128.25.172, master_port=42815
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) 2026-06-12 01:02:35.472 | INFO  | logging:info:2216 - [weight-sync] get_node_ip_address()=10.128.25.172 [repeated 3x across cluster]
(FSDPPolicyWorkerBase pid=364945) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/vllm/__init__.py:7: RuntimeWarning: Failed to read commit hash: [repeated 7x across cluster]
(FSDPPolicyWorkerBase pid=364945) No module named 'vllm._version' [repeated 7x across cluster]
(FSDPPolicyWorkerBase pid=364945) from .version import __version__, __version_tuple__ # isort:skip [repeated 7x across cluster]
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/torch/__init__.py:1617: UserWarning: Please use the new API settings to control TF32 behavior, such as torch.backends.cudnn.conv.fp32_precision = 'tf32' or torch.backends.cuda.matmul.fp32_precision = 'ieee'. Old settings, e.g, torch.backends.cuda.matmul.allow_tf32 = True, torch.backends.cudnn.allow_tf32 = True, allowTF32CuDNN() and allowTF32CuBLAS() will be deprecated after Pytorch 2.9. Please see https://pytorch.org/docs/main/notes/cuda.html#tensorfloat-32-tf32-on-ampere-and-later-devices (Triggered internally at /pytorch/aten/src/ATen/Context.cpp:80.)
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=304568, ip=10.128.25.165) (EngineCore_DP0 pid=304987) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=304566, ip=10.128.25.165) (EngineCore_DP0 pid=304984) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986) _C._set_float32_matmul_precision(precision)
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) [W612 01:05:00.280891184 socket.cpp:767] [c10d] The client socket cannot be initialized to connect to [jpbo-029-37.jupiter.internal]:33847 (errno: 97 - Address family not supported by protocol).
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) [W612 01:05:00.281316200 Utils.hpp:166] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator())
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) [rank0]:[W612 01:05:00.286139823 Utils.hpp:137] Warning: Environment variable TORCH_NCCL_TRACE_BUFFER_SIZE is deprecated; use TORCH_FR_BUFFER_SIZE instead (function operator())
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985)
Loading safetensors checkpoint shards: 0% Completed | 0/4 [00:00<?, ?it/s]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/torch/__init__.py:1617: UserWarning: Please use the new API settings to control TF32 behavior, such as torch.backends.cudnn.conv.fp32_precision = 'tf32' or torch.backends.cuda.matmul.fp32_precision = 'ieee'. Old settings, e.g, torch.backends.cuda.matmul.allow_tf32 = True, torch.backends.cudnn.allow_tf32 = True, allowTF32CuDNN() and allowTF32CuBLAS() will be deprecated after Pytorch 2.9. Please see https://pytorch.org/docs/main/notes/cuda.html#tensorfloat-32-tf32-on-ampere-and-later-devices (Triggered internally at /pytorch/aten/src/ATen/Context.cpp:80.) [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985)
Loading safetensors checkpoint shards: 25% Completed | 1/4 [00:04<00:14, 4.85s/it]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) [W612 01:05:00.280943535 socket.cpp:767] [c10d] The client socket cannot be initialized to connect to [jpbo-029-37-interconnect-1.jupiter.internal]:34269 (errno: 97 - Address family not supported by protocol). [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) [W612 01:05:00.281413062 Utils.hpp:166] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) [rank0]:[W612 01:05:00.286345611 Utils.hpp:137] Warning: Environment variable TORCH_NCCL_TRACE_BUFFER_SIZE is deprecated; use TORCH_FR_BUFFER_SIZE instead (function operator()) [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986)
Loading safetensors checkpoint shards: 0% Completed | 0/4 [00:00<?, ?it/s] [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985)
Loading safetensors checkpoint shards: 75% Completed | 3/4 [00:13<00:04, 4.48s/it] [repeated 8x across cluster]
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985)
(AsyncVLLMInferenceEngine pid=304568, ip=10.128.25.165) (EngineCore_DP0 pid=304987)
(AsyncVLLMInferenceEngine pid=304566, ip=10.128.25.165) (EngineCore_DP0 pid=304984)
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986)
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985) The tokenizer you are loading from '/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986)
Loading safetensors checkpoint shards: 100% Completed | 4/4 [00:15<00:00, 3.79s/it] [repeated 11x across cluster]
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) 2026-06-12 01:05:25.070 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:_create_engine:1301 - Initializing OpenAIServingChat with custom_chat_template read from: chat_templates/qwen3_thinking_acc.jinja2
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) (EngineCore_DP0 pid=380145) 2026-06-12 01:05:25.142 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:init_weight_update_communicator:223 - torch.distributed.get_rank(): 0, rank_offset: 5, rank: 5, world_size: 49, group_name: skyrl
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) [rank0]:[W612 01:05:25.941600277 socket.cpp:767] [c10d] The client socket cannot be initialized to connect to [jpbo-029-44-interconnect-1.jupiter.internal]:42815 (errno: 97 - Address family not supported by protocol).
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) (EngineCore_DP0 pid=380145) 2026-06-12 01:05:25.145 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:init_weight_update_communicator:234 - init_weight_update_communicator: master_address=10.128.25.172, master_port=42815,
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) /e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/torch/distributed/distributed_c10d.py:4876: UserWarning: barrier(): using the device under current context. You can specify `device_id` in `init_process_group` to mute this warning.
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) warnings.warn( # warn only once
(skyrl_entrypoint pid=364638) 2026-06-12 01:05:25.199 | INFO  | skyrl_train.trainer:init_weight_sync_state:874 - Initialized weight sync state for policy model and inference engines.
(skyrl_entrypoint pid=364638) 2026-06-12 01:05:25.200 | INFO  | skyrl_train.fully_async_trainer:_train_loop:544 - Finished: 'init_weight_sync_state', time cost: 175.76s
(skyrl_entrypoint pid=364638) 2026-06-12 01:05:25.200 | INFO  | skyrl_train.fully_async_trainer:_train_loop:548 - Started: 'sync_weights_to_inference_engines'
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) [rank0]:[W612 01:05:29.963020285 Utils.hpp:137] Warning: Environment variable TORCH_NCCL_TRACE_BUFFER_SIZE is deprecated; use TORCH_FR_BUFFER_SIZE instead (function operator())
(skyrl_entrypoint pid=364638) 2026-06-12 01:05:34.535 | INFO  | skyrl_train.fully_async_trainer:_train_loop:548 - Finished: 'sync_weights_to_inference_engines', time cost: 9.34s
(skyrl_entrypoint pid=364638) 2026-06-12 01:05:34.536 | INFO  | skyrl_train.callbacks.builtin:on_train_begin:270 - HFHubUploadCallback initialized: repo=laion/explore-tis-untrunc, upload_steps=5, export_path=/e/data1/datasets/playground/ot-baf/explore-tis-untrunc/explore-tis-untrunc/exports
(skyrl_entrypoint pid=364638)
Training Step Progress: 82it [00:00, ?it/s]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986) The tokenizer you are loading from '/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue. [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) 2026-06-12 01:05:25.070 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:_create_engine:1301 - Initializing OpenAIServingChat with custom_chat_template read from: chat_templates/qwen3_thinking_acc.jinja2 [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) (EngineCore_DP0 pid=249637) 2026-06-12 01:05:25.145 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:init_weight_update_communicator:223 - torch.distributed.get_rank(): 0, rank_offset: 24, rank: 24, world_size: 49, group_name: skyrl [repeated 47x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) [rank0]:[W612 01:05:25.561917791 socket.cpp:767] [c10d] The client socket cannot be initialized to connect to [jpbo-029-44.jupiter.internal]:42815 (errno: 97 - Address family not supported by protocol). [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) (EngineCore_DP0 pid=249637) 2026-06-12 01:05:25.148 | INFO | skyrl_train.inference_engines.vllm.vllm_engine:init_weight_update_communicator:234 - init_weight_update_communicator: master_address=10.128.25.172, master_port=42815,  [repeated 47x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) [rank0]:[W612 01:05:29.579234427 Utils.hpp:137] Warning: Environment variable TORCH_NCCL_TRACE_BUFFER_SIZE is deprecated; use TORCH_FR_BUFFER_SIZE instead (function operator()) [repeated 47x across cluster]
(skyrl_entrypoint pid=364638)
(skyrl_entrypoint pid=364638) 2026-06-12 01:08:53.812 | INFO  | skyrl_train.fully_async_trainer:_train_loop:604 - Started: 'step'
(skyrl_entrypoint pid=364638)
Generation Buffer Progress: 0%| | 0/64 [00:00<?, ?it/s]2026-06-12 01:08:53.812 | INFO  | skyrl_train.fully_async_trainer:_train_loop:607 - Started: 'wait_for_generation_buffer'
(RolloutCoordinator pid=301361, ip=10.128.25.162) 2026-06-12 01:08:53.816 | INFO | examples.terminal_bench.terminal_bench_generator:generate:560 - Starting batch generation for 8 trials (mode=training)
(RolloutCoordinator pid=350242, ip=10.128.25.161) 2026-06-12 01:09:06.223 | INFO | examples.terminal_bench.terminal_bench_generator:generate:560 - Starting batch generation for 8 trials (mode=training) [repeated 119x across cluster]
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e
(RolloutCoordinator pid=380389, ip=10.128.25.25) 2026-06-12 01:09:08.719 | INFO | examples.terminal_bench.terminal_bench_generator:generate:560 - Starting batch generation for 8 trials (mode=training) [repeated 218x across cluster]
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 95x across cluster]
(AsyncVLLMInferenceEngine pid=379729, ip=10.128.25.25) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 22x across cluster]
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 28x across cluster]
(AsyncVLLMInferenceEngine pid=301252, ip=10.128.25.163) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 13x across cluster]
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 10x across cluster]
(AsyncVLLMInferenceEngine pid=300698, ip=10.128.25.162) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 13x across cluster]
slurmstepd: error: *** JOB 736687 ON jpbo-026-33 CANCELLED AT 2026-06-12T01:10:56 ***
Preserving Ray logs to /e/data1/datasets/playground/ot-baf/explore-tis-untrunc/ray_logs/
2026-06-12 01:10:57.000 | ERROR | __main__:main:134 - Training failed: Task failed because the node it was running on is dead or unavailable. Node IP: 10.128.25.17, node ID: 96706d0fc7d05b397467667c5e336ac21712cf7e0c8bf1b2f4037765. This can happen if the node was preempted, had a hardware failure, or its raylet crashed unexpectedly. To see node death information, use `ray list nodes --filter node_id=96706d0fc7d05b397467667c5e336ac21712cf7e0c8bf1b2f4037765`, check the Ray dashboard cluster page, search the node ID in the GCS logs, or use `ray logs raylet.out -ip 10.128.25.17`.
2026-06-12 01:10:57.000 | INFO | __main__:main:137 - Shutting down Ray on head node...
(skyrl_entrypoint pid=364638) /e/scratch/jureap59/feuer1/miniforge3/lib/python3.12/multiprocessing/resource_tracker.py:279: UserWarning: resource_tracker: There appear to be 9 leaked semaphore objects to clean up at shutdown
(skyrl_entrypoint pid=364638) warnings.warn('resource_tracker: There appear to be %d '
(AsyncVLLMInferenceEngine pid=478789, ip=10.128.25.176) [proxychains] DLL init: proxychains-ng 4.17-git-9-g78ead0e [repeated 2x across cluster]
(skyrl_entrypoint pid=364638) [fd-monitor] Started monitoring (every 120s)
(skyrl_entrypoint pid=364638) [fd-monitor] [00:54:01] OK: 50 / 131,072 FDs open (0.0% of soft limit, hard limit: 131,072)
(skyrl_entrypoint pid=364638) [fd-monitor] [00:54:01] OK: RSS 1.38 GiB | node mem 135.5/858.0 GiB used (15.8%), avail 722.5 GiB
(skyrl_entrypoint pid=364638) ⚙️ Running in WANDB offline mode
(skyrl_entrypoint pid=364638) [fd-monitor] [00:56:01] OK: 87 / 131,072 FDs open (0.1% of soft limit, hard limit: 131,072)
(skyrl_entrypoint pid=364638) [fd-monitor] [00:56:01] OK: RSS 1.64 GiB | node mem 136.1/858.0 GiB used (15.9%), avail 721.9 GiB
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) WARNING 06-12 00:57:06 [arg_utils.py:1256] The global random seed is set to 69. Since VLLM_ENABLE_V1_MULTIPROCESSING is set to False, this may affect the random state of the Python process that launched vLLM.
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) INFO 06-12 00:57:06 [model.py:529] Resolved architecture: Qwen3ForCausalLM
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) INFO 06-12 00:57:06 [model.py:1549] Using max model len 32768
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) INFO 06-12 00:57:06 [arg_utils.py:1469] Using ray runtime env (env vars redacted): {'env_vars': {'NCCL_CUMEM_ENABLE': '***', 'NCCL_DEBUG': '***', 'NCCL_DEBUG_SUBSYS': '***', 'NCCL_SOCKET_FAMILY': '***', 'NCCL_SOCKET_IFNAME': '***', 'RAY_ADDRESS': '***', 'RAY_USE_UVLOOP': '***', 'SKYRL_WORKER_NCCL_TIMEOUT_IN_S': '***', 'TORCH_FR_BUFFER_SIZE': '***', 'TORCH_NCCL_ASYNC_ERROR_HANDLING': '***', 'TORCH_NCCL_DEBUG_INFO_TEMP_FILE': '***', 'TORCH_NCCL_DUMP_ON_TIMEOUT': '***', 'TORCH_NCCL_TRACE_BUFFER_SIZE': '***', 'VLLM_ALLOW_INSECURE_SERIALIZATION': '***', 'VLLM_ALLOW_RUNTIME_LORA_UPDATING': '***', 'VLLM_DISABLE_COMPILE_CACHE': '***', 'WANDB_API_KEY': '***'}}
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) INFO 06-12 00:57:06 [scheduler.py:224] Chunked prefill is enabled with max_num_batched_tokens=65536.
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) INFO 06-12 00:57:06 [vllm.py:690] Asynchronous scheduling is enabled.
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) WARNING 06-12 00:57:06 [vllm.py:728] Enforce eager set, overriding optimization level to -O0
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) INFO 06-12 00:57:06 [vllm.py:846] Cudagraph is disabled under eager mode
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) WARNING 06-12 00:57:06 [serial_utils.py:57] Allowing insecure serialization using pickle due to VLLM_ALLOW_INSECURE_SERIALIZATION=1
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) WARNING 06-12 00:57:06 [system_utils.py:140] We must use the `spawn` multiprocessing start method. Overriding VLLM_WORKER_MULTIPROC_METHOD to 'spawn'. See https://docs.vllm.ai/en/latest/usage/troubleshooting.html#python-multiprocessing for more information. Reasons: In a Ray actor and can only be spawned
(pid=441858, ip=10.128.25.172) ⚙️ Running in WANDB offline mode
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) (EngineCore_DP0 pid=443488) INFO 06-12 00:57:19 [core.py:97] Initializing a V1 LLM engine (vdev) with config: model='/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6', speculative_config=None, tokenizer='/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.bfloat16, max_seq_len=32768, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, data_parallel_size=1, disable_custom_all_reduce=False, quantization=None, enforce_eager=True, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=67, served_model_name=0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6, enable_prefix_caching=True, enable_chunked_prefill=True, pooler_config=None, compilation_config={'level': None, 'mode': <CompilationMode.NONE: 0>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['all'], 'splitting_ops': [], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_split_points': [65536], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.NONE: 0>, 'cudagraph_num_of_warmups': 0, 'cudagraph_capture_sizes': [], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'eliminate_noops': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False}, 'max_cudagraph_capture_size': 0, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': True, 'static_all_moe_layers': []}
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) WARNING 06-12 00:57:07 [arg_utils.py:1256] The global random seed is set to 68. Since VLLM_ENABLE_V1_MULTIPROCESSING is set to False, this may affect the random state of the Python process that launched vLLM. [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) INFO 06-12 00:57:07 [model.py:529] Resolved architecture: Qwen3ForCausalLM [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) INFO 06-12 00:57:07 [model.py:1549] Using max model len 32768 [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) INFO 06-12 00:57:07 [arg_utils.py:1469] Using ray runtime env (env vars redacted): {'env_vars': {'NCCL_CUMEM_ENABLE': '***', 'NCCL_DEBUG': '***', 'NCCL_DEBUG_SUBSYS': '***', 'NCCL_SOCKET_FAMILY': '***', 'NCCL_SOCKET_IFNAME': '***', 'RAY_ADDRESS': '***', 'RAY_USE_UVLOOP': '***', 'SKYRL_WORKER_NCCL_TIMEOUT_IN_S': '***', 'TORCH_FR_BUFFER_SIZE': '***', 'TORCH_NCCL_ASYNC_ERROR_HANDLING': '***', 'TORCH_NCCL_DEBUG_INFO_TEMP_FILE': '***', 'TORCH_NCCL_DUMP_ON_TIMEOUT': '***', 'TORCH_NCCL_TRACE_BUFFER_SIZE': '***', 'VLLM_ALLOW_INSECURE_SERIALIZATION': '***', 'VLLM_ALLOW_RUNTIME_LORA_UPDATING': '***', 'VLLM_DISABLE_COMPILE_CACHE': '***', 'WANDB_API_KEY': '***'}} [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) INFO 06-12 00:57:07 [scheduler.py:224] Chunked prefill is enabled with max_num_batched_tokens=65536. [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) INFO 06-12 00:57:07 [vllm.py:690] Asynchronous scheduling is enabled. [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) WARNING 06-12 00:57:07 [vllm.py:728] Enforce eager set, overriding optimization level to -O0 [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) INFO 06-12 00:57:07 [vllm.py:846] Cudagraph is disabled under eager mode [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) WARNING 06-12 00:57:07 [serial_utils.py:57] Allowing insecure serialization using pickle due to VLLM_ALLOW_INSECURE_SERIALIZATION=1 [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) WARNING 06-12 00:57:07 [system_utils.py:140] We must use the `spawn` multiprocessing start method. Overriding VLLM_WORKER_MULTIPROC_METHOD to 'spawn'. See https://docs.vllm.ai/en/latest/usage/troubleshooting.html#python-multiprocessing for more information. Reasons: In a Ray actor and can only be spawned [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) (EngineCore_DP0 pid=443505) INFO 06-12 00:57:26 [worker_base.py:289] Injected <class 'skyrl_train.inference_engines.vllm.vllm_engine.WorkerWrap'> into <class 'vllm.v1.worker.gpu_worker.Worker'> for extended collective_rpc calls ['_apply_fp8_weight_loader_patches', '_is_fp8_model', '_quantize_weights_for_fp8', '_restore_param_subclasses', '_undo_param_subclasses', 'begin_weight_update', 'destroy_weights_update_group', 'end_weight_update', 'init_weight_update_communicator', 'load_weights', 'read_named_weights', 'set_numa_affinity', 'test_rpc']
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) (EngineCore_DP0 pid=443494) INFO 06-12 00:57:19 [core.py:97] Initializing a V1 LLM engine (vdev) with config: model='/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6', speculative_config=None, tokenizer='/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.bfloat16, max_seq_len=32768, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, data_parallel_size=1, disable_custom_all_reduce=False, quantization=None, enforce_eager=True, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=78, served_model_name=0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6, enable_prefix_caching=True, enable_chunked_prefill=True, pooler_config=None, compilation_config={'level': None, 'mode': <CompilationMode.NONE: 0>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['all'], 'splitting_ops': [], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_split_points': [65536], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.NONE: 0>, 'cudagraph_num_of_warmups': 0, 'cudagraph_capture_sizes': [], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'eliminate_noops': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False}, 'max_cudagraph_capture_size': 0, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': True, 'static_all_moe_layers': []} [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) (EngineCore_DP0 pid=443488) INFO 06-12 00:57:27 [parallel_state.py:1234] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://10.128.25.174:47029 backend=nccl
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) (EngineCore_DP0 pid=443488) INFO 06-12 00:57:27 [parallel_state.py:1445] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank N/A
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) (EngineCore_DP0 pid=443488) INFO 06-12 00:57:28 [gpu_model_runner.py:4125] Starting to load model /e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6...
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) (EngineCore_DP0 pid=443488) INFO 06-12 00:57:29 [cuda.py:367] Using FLASH_ATTN attention backend out of potential backends: ['FLASH_ATTN', 'FLASHINFER', 'TRITON_ATTN', 'FLEX_ATTENTION'].
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) (EngineCore_DP0 pid=443488) INFO 06-12 00:57:44 [default_loader.py:293] Loading weights took 14.39 seconds
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) (EngineCore_DP0 pid=443484) INFO 06-12 00:57:27 [worker_base.py:289] Injected <class 'skyrl_train.inference_engines.vllm.vllm_engine.WorkerWrap'> into <class 'vllm.v1.worker.gpu_worker.Worker'> for extended collective_rpc calls ['_apply_fp8_weight_loader_patches', '_is_fp8_model', '_quantize_weights_for_fp8', '_restore_param_subclasses', '_undo_param_subclasses', 'begin_weight_update', 'destroy_weights_update_group', 'end_weight_update', 'init_weight_update_communicator', 'load_weights', 'read_named_weights', 'set_numa_affinity', 'test_rpc'] [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) (EngineCore_DP0 pid=443484) INFO 06-12 00:57:27 [parallel_state.py:1234] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://10.128.25.174:56675 backend=nccl [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) (EngineCore_DP0 pid=443484) INFO 06-12 00:57:27 [parallel_state.py:1445] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank N/A [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) (EngineCore_DP0 pid=443494) INFO 06-12 00:57:28 [gpu_model_runner.py:4125] Starting to load model /e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6... [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) (EngineCore_DP0 pid=443484) INFO 06-12 00:57:29 [cuda.py:367] Using FLASH_ATTN attention backend out of potential backends: ['FLASH_ATTN', 'FLASHINFER', 'TRITON_ATTN', 'FLEX_ATTENTION']. [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) (EngineCore_DP0 pid=443488) INFO 06-12 00:57:44 [gpu_model_runner.py:4222] Model loading took 15.27 GiB memory and 15.864247 seconds
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) (EngineCore_DP0 pid=443505) INFO 06-12 00:57:48 [gpu_worker.py:373] Available KV cache memory: 49.32 GiB
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) (EngineCore_DP0 pid=443505) INFO 06-12 00:57:48 [kv_cache_utils.py:1307] GPU KV cache size: 359,120 tokens
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) (EngineCore_DP0 pid=443505) INFO 06-12 00:57:48 [kv_cache_utils.py:1312] Maximum concurrency for 32,768 tokens per request: 10.96x
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) (EngineCore_DP0 pid=443505) INFO 06-12 00:57:48 [kernel_warmup.py:44] Skipping FlashInfer autotune because it is disabled.
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) (EngineCore_DP0 pid=443488) INFO 06-12 00:57:48 [core.py:278] init engine (profile, create kv cache, warmup model) took 4.25 seconds
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) (EngineCore_DP0 pid=443488) WARNING 06-12 00:57:49 [serial_utils.py:57] Allowing insecure serialization using pickle due to VLLM_ALLOW_INSECURE_SERIALIZATION=1
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) (EngineCore_DP0 pid=443488) INFO 06-12 00:57:49 [vllm.py:690] Asynchronous scheduling is enabled.
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) (EngineCore_DP0 pid=443488) WARNING 06-12 00:57:49 [vllm.py:735] Inductor compilation was disabled by user settings, optimizations settings that are only active during inductor compilation will be ignored.
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) (EngineCore_DP0 pid=443488) INFO 06-12 00:57:49 [vllm.py:846] Cudagraph is disabled under eager mode
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) (EngineCore_DP0 pid=443494) INFO 06-12 00:57:44 [default_loader.py:293] Loading weights took 14.27 seconds [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) WARNING 06-12 00:57:49 [model.py:1350] Default vLLM sampling parameters have been overridden by the model's `generation_config.json`: `{'temperature': 0.6, 'top_k': 20, 'top_p': 0.95}`. If this is not intended, please relaunch vLLM instance with `--generation-config vllm`.
(skyrl_entrypoint pid=364638) [fd-monitor] [00:58:01] OK: 88 / 131,072 FDs open (0.1% of soft limit, hard limit: 131,072)
(skyrl_entrypoint pid=364638) [fd-monitor] [00:58:01] OK: RSS 1.64 GiB | node mem 137.6/858.0 GiB used (16.0%), avail 720.3 GiB
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) (EngineCore_DP0 pid=443494) INFO 06-12 00:57:44 [gpu_model_runner.py:4222] Model loading took 15.27 GiB memory and 15.860758 seconds [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) (EngineCore_DP0 pid=443484) INFO 06-12 00:57:48 [gpu_worker.py:373] Available KV cache memory: 49.32 GiB [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) (EngineCore_DP0 pid=443484) INFO 06-12 00:57:48 [kv_cache_utils.py:1307] GPU KV cache size: 359,120 tokens [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) (EngineCore_DP0 pid=443484) INFO 06-12 00:57:48 [kv_cache_utils.py:1312] Maximum concurrency for 32,768 tokens per request: 10.96x [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) (EngineCore_DP0 pid=443488) INFO 06-12 00:57:48 [kernel_warmup.py:44] Skipping FlashInfer autotune because it is disabled. [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) (EngineCore_DP0 pid=443494) INFO 06-12 00:57:48 [core.py:278] init engine (profile, create kv cache, warmup model) took 4.22 seconds [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) (EngineCore_DP0 pid=443494) WARNING 06-12 00:57:49 [serial_utils.py:57] Allowing insecure serialization using pickle due to VLLM_ALLOW_INSECURE_SERIALIZATION=1 [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) (EngineCore_DP0 pid=443494) INFO 06-12 00:57:49 [vllm.py:690] Asynchronous scheduling is enabled. [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) (EngineCore_DP0 pid=443494) WARNING 06-12 00:57:49 [vllm.py:735] Inductor compilation was disabled by user settings, optimizations settings that are only active during inductor compilation will be ignored. [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) (EngineCore_DP0 pid=443494) INFO 06-12 00:57:49 [vllm.py:846] Cudagraph is disabled under eager mode [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) WARNING 06-12 00:57:49 [model.py:1350] Default vLLM sampling parameters have been overridden by the model's `generation_config.json`: `{'temperature': 0.6, 'top_k': 20, 'top_p': 0.95}`. If this is not intended, please relaunch vLLM instance with `--generation-config vllm`. [repeated 3x across cluster]
(skyrl_entrypoint pid=364638) [fd-monitor] [01:00:01] OK: 88 / 131,072 FDs open (0.1% of soft limit, hard limit: 131,072)
(skyrl_entrypoint pid=364638) [fd-monitor] [01:00:01] OK: RSS 1.64 GiB | node mem 137.7/858.0 GiB used (16.0%), avail 720.3 GiB
(AsyncVLLMInferenceEngine pid=326155, ip=10.128.25.27) WARNING 06-12 01:00:55 [arg_utils.py:1256] The global random seed is set to 86. Since VLLM_ENABLE_V1_MULTIPROCESSING is set to False, this may affect the random state of the Python process that launched vLLM.
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) INFO 06-12 01:00:55 [model.py:529] Resolved architecture: Qwen3ForCausalLM
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) INFO 06-12 01:00:55 [model.py:1549] Using max model len 32768
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) INFO 06-12 01:00:55 [arg_utils.py:1469] Using ray runtime env (env vars redacted): {'env_vars': {'NCCL_CUMEM_ENABLE': '***', 'NCCL_DEBUG': '***', 'NCCL_DEBUG_SUBSYS': '***', 'NCCL_SOCKET_FAMILY': '***', 'NCCL_SOCKET_IFNAME': '***', 'RAY_ADDRESS': '***', 'RAY_USE_UVLOOP': '***', 'SKYRL_WORKER_NCCL_TIMEOUT_IN_S': '***', 'TORCH_FR_BUFFER_SIZE': '***', 'TORCH_NCCL_ASYNC_ERROR_HANDLING': '***', 'TORCH_NCCL_DEBUG_INFO_TEMP_FILE': '***', 'TORCH_NCCL_DUMP_ON_TIMEOUT': '***', 'TORCH_NCCL_TRACE_BUFFER_SIZE': '***', 'VLLM_ALLOW_INSECURE_SERIALIZATION': '***', 'VLLM_ALLOW_RUNTIME_LORA_UPDATING': '***', 'VLLM_DISABLE_COMPILE_CACHE': '***', 'WANDB_API_KEY': '***'}}
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) INFO 06-12 01:00:55 [scheduler.py:224] Chunked prefill is enabled with max_num_batched_tokens=65536.
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) INFO 06-12 01:00:55 [vllm.py:690] Asynchronous scheduling is enabled.
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) WARNING 06-12 01:00:55 [vllm.py:728] Enforce eager set, overriding optimization level to -O0
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) INFO 06-12 01:00:55 [vllm.py:846] Cudagraph is disabled under eager mode
(AsyncVLLMInferenceEngine pid=478790, ip=10.128.25.176) WARNING 06-12 01:00:55 [serial_utils.py:57] Allowing insecure serialization using pickle due to VLLM_ALLOW_INSECURE_SERIALIZATION=1
(AsyncVLLMInferenceEngine pid=301250, ip=10.128.25.163) WARNING 06-12 01:00:55 [system_utils.py:140] We must use the `spawn` multiprocessing start method. Overriding VLLM_WORKER_MULTIPROC_METHOD to 'spawn'. See https://docs.vllm.ai/en/latest/usage/troubleshooting.html#python-multiprocessing for more information. Reasons: In a Ray actor and can only be spawned
(pid=364947) ⚙️ Running in WANDB offline mode
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) WARNING 06-12 01:00:55 [arg_utils.py:1256] The global random seed is set to 65. Since VLLM_ENABLE_V1_MULTIPROCESSING is set to False, this may affect the random state of the Python process that launched vLLM. [repeated 43x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) INFO 06-12 01:00:55 [model.py:529] Resolved architecture: Qwen3ForCausalLM [repeated 43x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) INFO 06-12 01:00:55 [model.py:1549] Using max model len 32768 [repeated 43x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) INFO 06-12 01:00:55 [arg_utils.py:1469] Using ray runtime env (env vars redacted): {'env_vars': {'NCCL_CUMEM_ENABLE': '***', 'NCCL_DEBUG': '***', 'NCCL_DEBUG_SUBSYS': '***', 'NCCL_SOCKET_FAMILY': '***', 'NCCL_SOCKET_IFNAME': '***', 'RAY_ADDRESS': '***', 'RAY_USE_UVLOOP': '***', 'SKYRL_WORKER_NCCL_TIMEOUT_IN_S': '***', 'TORCH_FR_BUFFER_SIZE': '***', 'TORCH_NCCL_ASYNC_ERROR_HANDLING': '***', 'TORCH_NCCL_DEBUG_INFO_TEMP_FILE': '***', 'TORCH_NCCL_DUMP_ON_TIMEOUT': '***', 'TORCH_NCCL_TRACE_BUFFER_SIZE': '***', 'VLLM_ALLOW_INSECURE_SERIALIZATION': '***', 'VLLM_ALLOW_RUNTIME_LORA_UPDATING': '***', 'VLLM_DISABLE_COMPILE_CACHE': '***', 'WANDB_API_KEY': '***'}} [repeated 43x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) INFO 06-12 01:00:55 [scheduler.py:224] Chunked prefill is enabled with max_num_batched_tokens=65536. [repeated 43x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) INFO 06-12 01:00:55 [vllm.py:690] Asynchronous scheduling is enabled. [repeated 43x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) WARNING 06-12 01:00:55 [vllm.py:728] Enforce eager set, overriding optimization level to -O0 [repeated 43x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) INFO 06-12 01:00:55 [vllm.py:846] Cudagraph is disabled under eager mode [repeated 43x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) WARNING 06-12 01:00:55 [serial_utils.py:57] Allowing insecure serialization using pickle due to VLLM_ALLOW_INSECURE_SERIALIZATION=1 [repeated 43x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) WARNING 06-12 01:00:55 [system_utils.py:140] We must use the `spawn` multiprocessing start method. Overriding VLLM_WORKER_MULTIPROC_METHOD to 'spawn'. See https://docs.vllm.ai/en/latest/usage/troubleshooting.html#python-multiprocessing for more information. Reasons: In a Ray actor and can only be spawned [repeated 43x across cluster]
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) (EngineCore_DP0 pid=301668) INFO 06-12 01:01:09 [core.py:97] Initializing a V1 LLM engine (vdev) with config: model='/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6', speculative_config=None, tokenizer='/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.bfloat16, max_seq_len=32768, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, data_parallel_size=1, disable_custom_all_reduce=False, quantization=None, enforce_eager=True, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=66, served_model_name=0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6, enable_prefix_caching=True, enable_chunked_prefill=True, pooler_config=None, compilation_config={'level': None, 'mode': <CompilationMode.NONE: 0>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['all'], 'splitting_ops': [], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_split_points': [65536], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.NONE: 0>, 'cudagraph_num_of_warmups': 0, 'cudagraph_capture_sizes': [], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'eliminate_noops': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False}, 'max_cudagraph_capture_size': 0, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': True, 'static_all_moe_layers': []}
(pid=441955, ip=10.128.25.172) ⚙️ Running in WANDB offline mode [repeated 6x across cluster]
(AsyncVLLMInferenceEngine pid=349371, ip=10.128.25.161) (EngineCore_DP0 pid=349999) INFO 06-12 01:01:15 [worker_base.py:289] Injected <class 'skyrl_train.inference_engines.vllm.vllm_engine.WorkerWrap'> into <class 'vllm.v1.worker.gpu_worker.Worker'> for extended collective_rpc calls ['_apply_fp8_weight_loader_patches', '_is_fp8_model', '_quantize_weights_for_fp8', '_restore_param_subclasses', '_undo_param_subclasses', 'begin_weight_update', 'destroy_weights_update_group', 'end_weight_update', 'init_weight_update_communicator', 'load_weights', 'read_named_weights', 'set_numa_affinity', 'test_rpc']
(AsyncVLLMInferenceEngine pid=379731, ip=10.128.25.25) (EngineCore_DP0 pid=380144) INFO 06-12 01:01:12 [core.py:97] Initializing a V1 LLM engine (vdev) with config: model='/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6', speculative_config=None, tokenizer='/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.bfloat16, max_seq_len=32768, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, data_parallel_size=1, disable_custom_all_reduce=False, quantization=None, enforce_eager=True, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=49, served_model_name=0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6, enable_prefix_caching=True, enable_chunked_prefill=True, pooler_config=None, compilation_config={'level': None, 'mode': <CompilationMode.NONE: 0>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['all'], 'splitting_ops': [], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_split_points': [65536], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.NONE: 0>, 'cudagraph_num_of_warmups': 0, 'cudagraph_capture_sizes': [], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'eliminate_noops': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_act_padding': False}, 'max_cudagraph_capture_size': 0, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': True, 'static_all_moe_layers': []} [repeated 43x across cluster]
(AsyncVLLMInferenceEngine pid=349371, ip=10.128.25.161) (EngineCore_DP0 pid=349999) INFO 06-12 01:01:15 [parallel_state.py:1234] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://10.128.25.161:54467 backend=nccl
(AsyncVLLMInferenceEngine pid=349371, ip=10.128.25.161) (EngineCore_DP0 pid=349999) INFO 06-12 01:01:16 [parallel_state.py:1445] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank N/A
(AsyncVLLMInferenceEngine pid=349371, ip=10.128.25.161) (EngineCore_DP0 pid=349999) INFO 06-12 01:01:16 [gpu_model_runner.py:4125] Starting to load model /e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6...
(AsyncVLLMInferenceEngine pid=349498, ip=10.128.25.161) (EngineCore_DP0 pid=349991) INFO 06-12 01:01:17 [cuda.py:367] Using FLASH_ATTN attention backend out of potential backends: ['FLASH_ATTN', 'FLASHINFER', 'TRITON_ATTN', 'FLEX_ATTENTION'].
(AsyncVLLMInferenceEngine pid=300698, ip=10.128.25.162) (EngineCore_DP0 pid=301108) INFO 06-12 01:01:19 [worker_base.py:289] Injected <class 'skyrl_train.inference_engines.vllm.vllm_engine.WorkerWrap'> into <class 'vllm.v1.worker.gpu_worker.Worker'> for extended collective_rpc calls ['_apply_fp8_weight_loader_patches', '_is_fp8_model', '_quantize_weights_for_fp8', '_restore_param_subclasses', '_undo_param_subclasses', 'begin_weight_update', 'destroy_weights_update_group', 'end_weight_update', 'init_weight_update_communicator', 'load_weights', 'read_named_weights', 'set_numa_affinity', 'test_rpc'] [repeated 39x across cluster]
(AsyncVLLMInferenceEngine pid=478659, ip=10.128.25.176) (EngineCore_DP0 pid=479197) INFO 06-12 01:01:32 [default_loader.py:293] Loading weights took 14.07 seconds
(AsyncVLLMInferenceEngine pid=300698, ip=10.128.25.162) (EngineCore_DP0 pid=301108) INFO 06-12 01:01:19 [parallel_state.py:1234] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://10.128.25.162:35647 backend=nccl [repeated 39x across cluster]
(AsyncVLLMInferenceEngine pid=379731, ip=10.128.25.25) (EngineCore_DP0 pid=380144) INFO 06-12 01:01:19 [parallel_state.py:1445] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank N/A [repeated 39x across cluster]
(AsyncVLLMInferenceEngine pid=379731, ip=10.128.25.25) (EngineCore_DP0 pid=380144) INFO 06-12 01:01:19 [gpu_model_runner.py:4125] Starting to load model /e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6... [repeated 39x across cluster]
(AsyncVLLMInferenceEngine pid=300699, ip=10.128.25.162) (EngineCore_DP0 pid=301118) INFO 06-12 01:01:20 [cuda.py:367] Using FLASH_ATTN attention backend out of potential backends: ['FLASH_ATTN', 'FLASHINFER', 'TRITON_ATTN', 'FLEX_ATTENTION']. [repeated 39x across cluster]
(AsyncVLLMInferenceEngine pid=478659, ip=10.128.25.176) (EngineCore_DP0 pid=479197) INFO 06-12 01:01:32 [gpu_model_runner.py:4222] Model loading took 15.27 GiB memory and 15.462349 seconds
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO cudaDriverVersion 13020
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO NCCL version 2.27.7+cuda13.0
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO NET/Plugin: Could not find: libnccl-net.so.
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_1:1/IB [2]mlx5_2:1/IB [3]mlx5_3:1/IB [RO]; OOB ib0:10.128.25.172<0>
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Initialized NET plugin IB
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Assigned NET plugin IB to comm
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Using network IB
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO DMA-BUF is available on GPU device 0
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO ncclCommInitRankConfig comm 0x400dfa6b40c0 rank 0 nranks 8 cudaDev 0 nvmlDev 0 busId 901000 commId 0xd750aa8fd3370a86 - Init START
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO RAS client listening socket at 127.0.0.1<28028>
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO NCCL_NET_GDR_LEVEL set by environment to LOC
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Setting affinity for GPU 0 to 0-71
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO NVLS multicast support is not available on dev 0 (NVLS_NCHANNELS 0)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO comm 0x400dfa6b40c0 rank 0 nRanks 8 nNodes 2 localRanks 4 localRank 0 MNNVL 0
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 00/08 : 0 1 2 3 7 6 5 4
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 01/08 : 0 4 5 6 7 3 2 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 02/08 : 0 3 1 5 4 7 6 2
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 03/08 : 0 3 2 6 4 7 5 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 04/08 : 0 1 2 3 7 6 5 4
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 05/08 : 0 4 5 6 7 3 2 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 06/08 : 0 3 1 5 4 7 6 2
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 07/08 : 0 3 2 6 4 7 5 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Trees [0] 1/4/-1->0->-1 [1] -1/-1/-1->0->3 [2] 1/-1/-1->0->2 [3] 2/-1/-1->0->3 [4] 1/-1/-1->0->4 [5] -1/-1/-1->0->3 [6] 1/-1/-1->0->2 [7] 2/-1/-1->0->3
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO P2P Chunksize set to 131072
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO PROFILER/Plugin: Could not find: libnccl-profiler.so.
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Check P2P Type isAllDirectP2p 1 directMode 0
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO [Proxy Service] Device 0 CPU core 49
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442377 [0] NCCL INFO [Proxy Service UDS] Device 0 CPU core 50
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 00/0 : 0[0] -> 1[1] via P2P/IPC
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x40118c000000 size 2097152 ipcDesc 0x400ed4008b70
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 04/0 : 0[0] -> 1[1] via P2P/IPC
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x40118c200000 size 2097152 ipcDesc 0x400ed4009b30
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 02/0 : 0[0] -> 3[3] via P2P/IPC
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x40118c400000 size 2097152 ipcDesc 0x400ed400a940
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 03/0 : 0[0] -> 3[3] via P2P/IPC
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x40118c600000 size 2097152 ipcDesc 0x400ed400b730
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 06/0 : 0[0] -> 3[3] via P2P/IPC
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x40118c800000 size 2097152 ipcDesc 0x400ed400c500
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 07/0 : 0[0] -> 3[3] via P2P/IPC
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x40118ca00000 size 2097152 ipcDesc 0x400ed400d2d0
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442383 [0] NCCL INFO [Proxy Progress] Device 0 CPU core 51
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 00/0 : 4[0] -> 0[0] [receive] via NET/IB/0
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 04/0 : 4[0] -> 0[0] [receive] via NET/IB/0
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 01/0 : 0[0] -> 4[0] [send] via NET/IB/0
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 05/0 : 0[0] -> 4[0] [send] via NET/IB/0
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x40118cc00000 size 10485760 ipcDesc 0x400ed4010180
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x40118d600000 size 10485760 ipcDesc 0x400ed4010f50
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x40118e000000 size 10485760 ipcDesc 0x400ed4010f50
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x40118ea00000 size 10485760 ipcDesc 0x400ed4010f50
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x40118f400000 size 10485760 ipcDesc 0x400ed4010f50
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x40118fe00000 size 10485760 ipcDesc 0x400ed4010f50
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Imported shareable buffer device 0 size 10485760 ptr 0x401190800000
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Imported shareable buffer device 0 size 10485760 ptr 0x401191200000
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Imported shareable buffer device 0 size 10485760 ptr 0x401191c00000
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Imported shareable buffer device 0 size 10485760 ptr 0x401192600000
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Imported shareable buffer device 0 size 10485760 ptr 0x401193000000
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Imported shareable buffer device 0 size 10485760 ptr 0x401193a00000
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Imported shareable buffer device 0 size 2097152 ptr 0x401194400000
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Imported shareable buffer device 0 size 2097152 ptr 0x401194600000
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Imported shareable buffer device 0 size 2097152 ptr 0x401194800000
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Imported shareable buffer device 0 size 2097152 ptr 0x401194a00000
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Imported shareable buffer device 0 size 2097152 ptr 0x401194c00000
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Imported shareable buffer device 0 size 2097152 ptr 0x401194e00000
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Connected all rings, use ring PXN 0 GDR 0
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 02/0 : 0[0] -> 1[1] via P2P/IPC
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x401195000000 size 2097152 ipcDesc 0x400ed4015c30
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 06/0 : 0[0] -> 1[1] via P2P/IPC
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x401195200000 size 2097152 ipcDesc 0x400ed4015c30
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 02/0 : 0[0] -> 2[2] via P2P/IPC
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x401195400000 size 2097152 ipcDesc 0x400ed4015c30
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 03/0 : 0[0] -> 2[2] via P2P/IPC
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x401195600000 size 2097152 ipcDesc 0x400ed4015c30
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 06/0 : 0[0] -> 2[2] via P2P/IPC
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x401195800000 size 2097152 ipcDesc 0x400ed4015c30
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 07/0 : 0[0] -> 2[2] via P2P/IPC
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x401195a00000 size 2097152 ipcDesc 0x400ed4015c30
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 01/0 : 0[0] -> 3[3] via P2P/IPC
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x401195c00000 size 2097152 ipcDesc 0x400ed4015c30
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 05/0 : 0[0] -> 3[3] via P2P/IPC
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x401195e00000 size 2097152 ipcDesc 0x400ed4015c30
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 00/0 : 0[0] -> 4[0] [send] via NET/IB/0
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO Channel 04/0 : 0[0] -> 4[0] [send] via NET/IB/0
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x401196000000 size 10485760 ipcDesc 0x400ed4015c30
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0] NCCL INFO Allocated shareable buffer 0x401196a00000 size 10485760 ipcDesc 0x400ed4015c30
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442374 [0]
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442347 [0]
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442376 [0] NCCL INFO Allocated
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365456 [0] NCCL INFO Connected all trees
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365456 [0] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365456 [0] NCCL INFO 8 coll channels, 8 collnet channels, 0 nvls channels, 8 p2p channels, 2 p2p channels per peer
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365456 [0] NCCL INFO TUNER/Plugin: Could not find: libnccl-tuner.so. Using internal tuner plugin.
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365456 [0] NCCL INFO ncclCommInitRankConfig comm 0x400e412e5990 rank 5 nranks 8 cudaDev 0 nvmlDev 1 busId 1901000 commId 0xd750aa8fd3370a86 - Init COMPLETE
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365456 [0] NCCL INFO Init timings - ncclCommInitRankConfig: rank 5 nranks 8 total 2.83 (kernels 0.32, alloc 1.84, bootstrap 0.00, allgathers 0.00, topo 0.02, graphs 0.01, connections 0.63, rest 0.00)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442346 [0] NCCL INFO CC Off, workFifoBytes 1048576
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount 0 sendbuff 0x401340000000 recvbuff 0x401340000000 count 622329856 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 00/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 01/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 02/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 03/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 04/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 05/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 06/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 07/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 08/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 09/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 10/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 11/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 12/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 13/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 14/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 15/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 16/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 17/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 18/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 19/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 20/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 21/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 22/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 23/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 24/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 25/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 26/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 27/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 28/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 29/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 30/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 31/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 32/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 33/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 34/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 35/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 36/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 37/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 38/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 39/40 : 0 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Check P2P Type isAllDirectP2p 0 directMode 0
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Channel 01/0 : 0[0] -> 1[0] [send] via NE
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442389 [0] NCCL INFO Channel 01/0 : 0[1] -> 1[1] [send]
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) e400000
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442391 [0] NCCL INFO Channel 01/0 : 0[3] -> 1[3] [se
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) shareable buffer 0x400f1fc00000 size 2097152 ipcDesc 0x400f6429ffb0
(AsyncVLLMInferenceEngine pid=301251, ip=10.128.25.163) (EngineCore_DP0 pid=301662) INFO 06-12 01:01:36 [gpu_worker.py:373] Available KV cache memory: 49.32 GiB
(AsyncVLLMInferenceEngine pid=301251, ip=10.128.25.163) (EngineCore_DP0 pid=301662) INFO 06-12 01:01:36 [kv_cache_utils.py:1307] GPU KV cache size: 359,120 tokens
(AsyncVLLMInferenceEngine pid=301251, ip=10.128.25.163) (EngineCore_DP0 pid=301662) INFO 06-12 01:01:36 [kv_cache_utils.py:1312] Maximum concurrency for 32,768 tokens per request: 10.96x
(FSDPPolicyWorkerBase pid=364947) jpbo-026
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:
(FSDPPolicyWorkerBase pid=364944) jpbo
(AsyncVLLMInferenceEngine pid=478789, ip=10.128.25.176) (EngineCore_DP0 pid=479189) INFO 06-12 01:01:36 [kernel_warmup.py:44] Skipping FlashInfer autotune because it is disabled.
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) T/IB/0
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO Connected binomial trees
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442393 [0] NCCL INFO CC Off, workFifoBytes 1048576
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) via NET/IB/1
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) nd] via NET/IB/3
(AsyncVLLMInferenceEngine pid=316510, ip=10.128.25.28) (EngineCore_DP0 pid=317118) INFO 06-12 01:01:36 [core.py:278] init engine (profile, create kv cache, warmup model) took 3.74 seconds
(FSDPPolicyWorkerBase pid=364947) jp
(FSDPPolicyWorkerBase pid=364946) fc00000
(FSDPPolicyWorkerBase pid=364944) ed30
(FSDPPolicyWorkerBase pid=364945) 400ff000ed30
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365512 [0] NCCL INFO Imported shareable buffer device 0
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442407 [0] NCCL INFO ncclCommInitRankConfig comm 0x400dfaa9fd00 rank 0 nranks 4 cudaDev 0 nvmlDev 0 busId 901000 commId 0x8d21f48cdf4c109b - Ini
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:44
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) ff800ed30
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442412 [0] NCCL INFO Alloc
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) 0
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:4419
(FSDPPolicyWorkerBase pid=364947)
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400f40000000 count 155582464 datatype 9 op 0 root 0 comm 0x400e416caff0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365517 [
(FSDPPolicyWorkerBase pid=364946) IPC
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x4013528c0000 count 155582464 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401365180000 count 155582464 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401377a40000 count 155582464 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401100800000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401101000000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401101800000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401116a00000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401116c00000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401116e00000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x4011c3a00000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x4011c3c00000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x4011c3e00000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401100800000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401101000000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401101800000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa02a40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa02a80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa02ac0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa02e40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa02e80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa02ec0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401109000000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40110a800000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40110c000000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401135400000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401136c00000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401138400000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401109000000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40110a800000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40110c000000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount a sendbuff 0x400edfa00000 recvbuff 0x400edfa00000 count 4096 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa00800 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa01000 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa01800 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount b sendbuff 0x400edfa31400 recvbuff 0x400edfa31400 count 4096 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa31c00 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa32400 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa32c00 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount c sendbuff 0x401135400000 recvbuff 0x401135400000 count 16777216 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401135c00000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401136400000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401136c00000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount d sendbuff 0x401103000000 recvbuff 0x401103000000 count 4194304 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401103200000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401103400000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401103600000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount a sendbuff 0x401103800000 recvbuff 0x401103800000 count 4194304 datatype 9 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount e sendbuff 0x401103800000 recvbuff 0x401103800000 count 4194304 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401103a00000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401103c00000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401103e00000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount b sendbuff 0x401135400000 recvbuff 0x401135400000 count 16777216 datatype 9 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount f sendbuff 0x401135400000 recvbuff 0x401135400000 count 16777216 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401135c00000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401136400000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401136c00000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount c sendbuff 0x400edfa03e00 recvbuff 0x400edfa03e00 count 128 datatype 9 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa03e40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa03e80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa03ec0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount c sendbuff 0x400edfa04200 recvbuff 0x400edfa04200 count 128 datatype 9 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa04240 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa04280 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa042c0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount c sendbuff 0x401107800000 recvbuff 0x401107800000 count 50331648 datatype 9 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401109000000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40110a800000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40110c000000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount d sendbuff 0x40113b400000 recvbuff 0x40113b400000 count 50331648 datatype 9 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113cc00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113e400000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113fc00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount e sendbuff 0x401107800000 recvbuff 0x401107800000 count 50331648 datatype 9 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401109000000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40110a800000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40110c000000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount f sendbuff 0x400edfa00000 recvbuff 0x400edfa00000 count 4096 datatype 9 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa00800 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa01000 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa01800 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount f sendbuff 0x400edfa31c00 recvbuff 0x400edfa31c00 count 4096 datatype 9 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa32400 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa32c00 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa33400 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount f sendbuff 0x401107800000 recvbuff 0x401107800000 count 16777216 datatype 9 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401108000000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401108800000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401109000000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401109a00000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401109c00000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401109e00000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401107c00000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401107e00000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401108000000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401108c00000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401109400000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401109c00000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa04240 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa04280 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa042c0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa00a40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa00a80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa00ac0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113cc00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113e400000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113fc00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401341800000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401343000000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401344800000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113cc00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113e400000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113fc00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa32400 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa32c00 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa33400 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa34400 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa34c00 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa35400 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113bc00000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113c400000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113cc00000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113d600000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113d800000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113da00000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113b600000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113b800000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113ba00000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113c400000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113cc00000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40113d400000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa01a40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa01a80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa01ac0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa01e40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa01e80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa01ec0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401341800000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401343000000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401344800000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401347800000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401349000000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134a800000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401341800000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401343000000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401344800000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa32400 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa32c00 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa33400 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa34c00 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa35400 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa35c00 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401340800000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401341000000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401341800000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401140e00000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401141000000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401141200000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401340400000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401340600000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401340800000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401341200000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401341a00000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401342200000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa01e40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa01e80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa01ec0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa32640 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa32680 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa326c0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401342200000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401343a00000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401345200000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401349a00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134b200000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134ca00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134fa00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401351200000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401352a00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa34c00 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa35400 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa35c00 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa36c00 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa37400 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa37c00 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401344200000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401344a00000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401345200000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401346400000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401346600000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401346800000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401343c00000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401343e00000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401344000000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401348a00000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401349200000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401349a00000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa33640 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa33680 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa336c0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa33a40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa33a80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa33ac0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401349a00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134b200000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134ca00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134fa00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401351200000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401352a00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401355a00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401357200000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401358a00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa34c00 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa35400 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa35c00 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa37400 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa37c00 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa38400 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134ba00000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134c200000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134ca00000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134d400000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134d600000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134d800000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134b400000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134b600000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134b800000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134c400000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134cc00000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134d400000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa33a40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa33a80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa33ac0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa34e40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa34e80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa34ec0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134d400000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134ec00000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401350400000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401354c00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401356400000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401357c00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40135ac00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40135c400000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40135dc00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa37400 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa37c00 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa38400 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa39400 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa39c00 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3a400 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134f400000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134fc00000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401350400000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401351600000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401351800000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401351a00000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134f000000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134f200000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134f400000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401353c00000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401354400000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401354c00000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa35e40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa35e80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa35ec0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa36240 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa36280 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa362c0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401354c00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401356400000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401357c00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40135c400000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40135dc00000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40135f400000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401362400000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401363c00000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401365400000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa37400 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa37c00 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa38400 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa39c00 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3a400 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3ac00 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401356c00000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401357400000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401357c00000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401358e00000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401359000000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401359200000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134f800000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134fa00000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134fc00000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401356c00000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401357400000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401357c00000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa36240 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa36280 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa362c0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa37640 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa37680 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa376c0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40135c400000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40135dc00000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40135f400000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401362400000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401363c00000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401365400000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401368400000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401369c00000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136b400000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa39c00 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3a400 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3ac00 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3bc00 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3c400 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3cc00 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40135e400000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40135ec00000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40135f400000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134f800000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134fa00000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40134fc00000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401350000000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401350200000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401350400000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40135e400000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40135ec00000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40135f400000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa38640 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa38680 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa386c0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa38a40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa38a80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa38ac0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40135f400000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401360c00000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401362400000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401366c00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401368400000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401369c00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136cc00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136e400000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136fc00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa39c00 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3a400 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3ac00 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3c400 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3cc00 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3d400 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401361400000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401361c00000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401362400000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401362e00000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401363000000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401363200000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401363600000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401363800000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401363a00000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401361400000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401361c00000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401362400000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa38a40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa38a80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa38ac0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa39e40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa39e80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa39ec0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401366c00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401368400000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401369c00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136cc00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136e400000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136fc00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401372c00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401374400000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401375c00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3c400 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3cc00 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3d400 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3e400 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3ec00 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3f400 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401368c00000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401369400000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401369c00000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401363600000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401363800000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401363a00000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401368800000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401368a00000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401368c00000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401369600000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401369e00000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136a600000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3ae40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3ae80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3aec0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3b240 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3b280 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3b2c0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136a600000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136be00000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136d600000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401371e00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401373600000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401374e00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401377e00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401379600000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137ae00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3c400 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3cc00 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3d400 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3ec00 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3f400 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3fc00 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136c600000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136ce00000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136d600000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136e800000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136ea00000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136ec00000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136c000000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136c200000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40136c400000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401370e00000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401371600000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401371e00000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3b240 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3b280 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3b2c0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3c640 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3c680 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3c6c0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401371e00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401373600000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401374e00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401377e00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365515 [0
(FSDPPolicyWorkerBase pid=364946) (nil) recvbuff 0x401379600000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137ae00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137de00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137f600000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401380e00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3ec00 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3f400 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3fc00 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa40c00 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa41400 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa41c00 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401384600000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401384e00000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401385600000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401386000000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401386200000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401386400000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401384000000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401384200000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401384400000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401385000000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401385800000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401386000000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3d640 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3d680 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3d6c0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3da40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3da80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3dac0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401373600000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401374e00000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401376600000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401379600000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137ae00000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137c600000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401373600000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401374e00000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401376600000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3ec00 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3f400 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3fc00 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa41400 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa41c00 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa42400 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401372600000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401372e00000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401373600000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401389a00000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401389c00000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401389e00000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401372000000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401372200000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401372400000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401372e00000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401373600000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401373e00000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3da40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3da80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3dac0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3ee40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3ee80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3eec0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401373e00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401375600000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401376e00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137b600000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137ce00000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137e600000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401373e00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401375600000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401376e00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa41400 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa41c00 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa42400 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa43400 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa43c00 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa44400 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137be00000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137c600000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137ce00000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401381800000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401381a00000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0]
(FSDPPolicyWorkerBase pid=364946) NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401381c00000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137b800000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137ba00000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137bc00000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137c600000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137ce00000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137d600000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount aa sendbuff 0x400edfa3fe00 recvbuff 0x400edfa3fe00 count 128 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3fe40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3fe80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa3fec0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount ab sendbuff 0x400edfa40200 recvbuff 0x400edfa40200 count 128 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa40240 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa40280 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa402c0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount ac sendbuff 0x401372600000 recvbuff 0x401372600000 count 50331648 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401373e00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401375600000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401376e00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount ad sendbuff 0x40164f000000 recvbuff 0x40164f000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401650800000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401652000000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401653800000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount ae sendbuff 0x401372600000 recvbuff 0x401372600000 count 50331648 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401373e00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401375600000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401376e00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount af sendbuff 0x400edfa40c00 recvbuff 0x400edfa40c00 count 4096 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa41400 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa41c00 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa42400 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa43c00 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa44400 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edf
(FSDPPolicyWorkerBase pid=364946) a44c00 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401651000000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401651800000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401652000000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137f000000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137f200000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137f400000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137f800000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137fa00000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137fc00000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401651000000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401651800000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401652000000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa40240 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa40280 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa402c0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa41640 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa41680 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa416c0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401373e00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401375600000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401376e00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401656800000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401658000000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401659800000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401373e00000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401375600000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401376e00000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount ba sendbuff 0x400edfa43400 recvbuff 0x400edfa43400 count 4096 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa43c00 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa44400 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa44c00 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount bb sendbuff 0x400edfa45400 recvbuff 0x400edfa45400 count 4096 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa45c00 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa46400 count 1024 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa46c00 count 1024 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount bc sendbuff 0x401372600000 recvbuff 0x401372600000 count 16777216 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401372e00000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401373600000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401373e00000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount bd sendbuff 0x401374600000 recvbuff 0x401374600000 count 4194304 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401374800000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401374a00000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401374c00000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount be sendbuff 0x401372800000 recvbuff 0x401372800000 count 4194304 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401372a00000 count 1048576 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401372c00000 count 1048576 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401372e00000 count 1048576 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount bf sendbuff 0x401373200000 recvbuff 0x401373200000 count 16777216 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401373a00000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401374200000 count 4194304 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401374a00000 count 4194304 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa42640 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa42680 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa426c0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa42a40 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa42a80 count 32 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa42ac0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401656800000 count 12582912 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401658000000 count 12582912 datatype 9 op 0 root 2 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401659800000 count 12582912 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:3
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) t COMPLETE
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO Broadcast: opCount 8b sendbuff 0x4010910000
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount ca sendbuff 0x401605800000 recvbuff 0x401605800000 count 16777216 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount cb sendbuff 0x400edfa42a00 recvbuff 0x400edfa42a00 count 128 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opC
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) ated shareable buffer 0x32e600000 size 2097152 ipcDesc 0x400ff800ed30
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442312 [0] NCCL INFO Broadcast: opCount 90 sendbuff 0x401091000000 recvbuff 0x401091000000 count 16777216 datatype 9 op 0 root 0 comm 0x400e255
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) 00 recvbuff 0x401091000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e115b17e0 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO Broadcast: opCount 63 sendbuff 0x400e99e13e00 recvbuff 0x400e99e13e00 count 4096 datatyp
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) af260 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:4419
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442310 [0] NCCL INFO Broadcast: opCount 63 sendbuff 0x400e99e13e00 recvbuff 0x400e99e13e00 count 4096 datatype
(FSDPPolicyWorkerBase pid=364946) ount 83 sendbuff 0x400edfa43e00 recvbuff 0x400edfa43e00 count 128 datatype 9 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount cc sendbuff 0x400edfa43e00 recvbuff 0x400edfa43e00 count 128 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount cd sendbuff 0x401655000000 recvbuff 0x401655000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount ce sendbuff 0x40160b000000 recvbuff 0x40160b000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount cf sendbuff 0x401655000000 recvbuff 0x401655000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount da sendbuff 0x401655000000 recvbuff 0x401655000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount db sendbuff 0x400edfa45c00 recvbuff 0x400edfa45c00 count 4096 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount dc sendbuff 0x400edfa48400 recvbuff 0x400edfa48400 count 4096 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount dd sendbuff 0x401611000000 recvbuff 0x401611000000 count 16777216 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount de sendbuff 0x401613000000 recvbuff 0x401613000000 count 4194304 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount df sendbuff 0x401611000000 recvbuff 0x401611000000 count 4194304 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount ea sendbuff 0x401617000000 recvbuff 0x401617000000 count 4194304 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount eb sendbuff 0x401617800000 recvbuff 0x401617800000 count 16777216 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount ec sendbuff 0x400edfa47600 recvbuff 0x400edfa47600 count 128 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount ed sendbuff 0x400edfa47a00 recvbuff 0x400edfa47a00 count 128 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount ee sendbuff 0x401617000000 recvbuff 0x401617000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount ef sendbuff 0x4013e0000000 recvbuff 0x4013e0000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount f9 sendbuff 0x4013e0000000 recvbuff 0x4013e0000000 count 5033164
(FSDPPolicyWorkerBase pid=364945) size 10485760 ptr 0x334400000
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO Broadcast: opCount 8 sendbuff 0x400e99e02e00 recvbuff 0x400e99e02e00 count 4096 datatype 9 op 0
(FSDPPolicyWorkerBase pid=364946) 8 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount fa sendbuff 0x4013e6000000 recvbuff 0x4013e6000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount fb sendbuff 0x4013e0000000 recvbuff 0x4013e0000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount fc sendbuff 0x400edfa4ac00 recvbuff 0x400edfa4ac00 count 4096 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount fd sendbuff 0x400edfa4cc00 recvbuff 0x400edfa4cc00 count 4096 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount fe sendbuff 0x4013e0000000 recvbuff 0x4013e0000000 count 16777216 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount ff sendbuff 0x40161b800000 recvbuff 0x40161b800000 count 4194304 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount 102 sendbuff 0x400edfa49e00 recvbuff 0x400edfa49e00 count 128 datatype 9 op 0 ro
(FSDPPolicyWorkerBase pid=364944) ] NCCL INFO Allocated shareable buffer 0x401024600000 size 10485760 ipcDesc 0x400fd000ed30
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO Broadcast: opCount 8 sendbuff 0x400e99e02e00 recvbuff 0x400e99e02e00 count 4096 datatype 9 op 0 r
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Br
(FSDPPolicyWorkerBase pid=364947) root 0 comm 0x400e412e5990 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:36
(FSDPPolicyWorkerBase pid=364944) oot 0 comm 0x400e412e4700 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364
(FSDPPolicyWorkerBase pid=364945) oadcast: opCount 10 sendbuff 0x400eb9e00e00 recvbuff 0x400eb9e00e00 count 128 datatype 9 op 0 root 0 comm 0x400e615a9820 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 1f sendbuff 0x400ed9000000 recvbuff 0x400ed
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO Recv: opCount 0 sendbuff
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400ed0000000 count 4194304 datatype 9 op 0 root 0 comm 0x400e6
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO Broadcast: opCount 37 sendbuff 0x400e99e07e00 recvbuff 0x400e99e07e00 coun
(FSDPPolicyWorkerBase pid=364945) jpb
(FSDPPolicyWorkerBase pid=364947) t 4096 datatype 9 op 0 root 0 comm 0x400e415b09a0 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL I
(FSDPPolicyWorkerBase pid=364946) ot 0 comm 0x400e06983940 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount aa sendbuff 0x4013ea800000 recvbuff 0x4013ea800000 count 4194304 datatype 9 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount ab sendbuff 0x4013eb000000 recvbuff 0x4013eb000000 count 4194304 datatype 9 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount 10b sendbuff 0x4013eb000000 recvbuff 0x4013eb000000 count 4194304 datatype 9 op 0 root 0 comm 0x400e06983940 [nranks=2] stream (
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL IN
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount
(FSDPPolicyWorkerBase pid=364947) NFO Broadcast: opCount 37 sendbuff 0x400ed0c00000 recvbuff 0x400ed0c00000 count 50331648 datatype 9 op 0 root 0 comm 0x400e412e5990 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) rec
(FSDPPolicyWorkerBase pid=364944) FO Broadcast: opCount 37 sendbuff 0x400ed0c00000 recvbuff 0x400ed0c00000 count 50331648 datatype 9 op 0 root 0 comm 0x400e412e4700 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recv
(FSDPPolicyWorkerBase pid=364945) 4b sendbuff 0x400eef400000 recvbuff 0x400eef400000 count 50331648 datatype 9 op 0 root 0 comm 0x400e615a9820 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400eb9e0b000 count 32 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nra
(FSDPPolicyWorkerBase pid=364947) vbuff 0x400e99e0a600 count 1024 datatype 9 op 0 root 0 comm 0x400e416caff0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364944) buff 0x400e99e0a600 count 1024 datatype 9 op 0 root 0 comm 0x400e416cc220 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO Broadcast: opCount 53 sendbuff 0x401071000000 recvbuff 0x401071000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e412e4700 [nranks=8] stream
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:36
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO Broadcast: opCount 53 sendbuff 0x401071000000 recvbuff 0x401071000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e412e5990 [nranks=8] strea
(FSDPPolicyWorkerBase pid=364944) (nil)
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO Broadcast:
(FSDPPolicyWorkerBase pid=364947) m (nil)
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO Broadcast
(FSDPPolicyWorkerBase pid=364944) opCount 5c sendbuff 0x401071000000 recvbuff 0x401071000000 count 16777216 datatype 9 op 0 root 0 comm 0x400e412e4700 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recv
(FSDPPolicyWorkerBase pid=364947) : opCount 5c sendbuff 0x401071000000 recvbuff 0x401071000000 count 16777216 datatype 9 op 0 root 0 comm 0x400e412e5990 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) rec
(FSDPPolicyWorkerBase pid=364946) nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount ac sendbuff 0x4013e0000000 recvbuff 0x4013e0000000 count 16777216 datatype 9 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount ad sendbuff 0x400edfa4a200 recvbuff 0x400edfa4a200 count 128 datatype 9 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount ad sendbuff 0x400edfa4b600 recvbuff 0x400edfa4b600 count 128 datatype 9 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount ad sendbuff 0x4013e0000000 recvbuff 0x4013e0000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount ae sendbuff 0x4013f2000000 recvbuff 0x4013f2000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Broadcast: opCount af sendbuff 0x4013e0000000 recvbuff 0x4013e0000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send:
(FSDPPolicyWorkerBase pid=364944) buff 0x40107c000000 count 4194304 datatype 9 op 0 root 0 comm 0x400e416cc220 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO Broadcast: opCount ad sendbuff 0x401036c00000 recvbuff 0x401036c00000 count 50331648 datatype 9 op 0
(FSDPPolicyWorkerBase pid=364945) 9 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x401074000000 count 12582912 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4
(FSDPPolicyWorkerBase pid=364947) vbuff 0x40107c000000 count 4194304 datatype 9 op 0 root 0 comm 0x400e416caff0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364944) jpbo-0
(FSDPPolicyWorkerBase pid=364945) ] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0]
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO Broadc
(FSDPPolicyWorkerBase pid=364946) opCount 0 sendbuff (nil) recvbuff 0x4013e0800000 count 4194304 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) re
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO Broadca
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount c1 sendbuff 0x400eb9e15200 rec
(FSDPPolicyWorkerBase pid=364947) ast: opCount 83 sendbuff 0x400e99e16200 recvbuff 0x400e99e16200 count 128 datatype 9 op 0 root 0 comm 0x400e412e5990 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400f80000000 c
(FSDPPolicyWorkerBase pid=364944) st: opCount 83 sendbuff 0x400e99e16200 recvbuff 0x400e99e16200 count 128 datatype 9 op 0 root 0 comm 0x400e412e4700 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount d0 sendbuff 0x400eb9e16e00 recvbuff 0x400eb9e16e00 count 4096 datatype 9 o
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0]
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) e 9 op 0 root 0 comm 0x400e112e5db0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029
(FSDPPolicyWorkerBase pid=364947) ount 12582912 datatype 9 op 0 root 0 comm 0x400e416caff0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364944) jpbo-026
(FSDPPolicyWorkerBase pid=364945) p 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcas
(FSDPPolicyWorkerBase pid=364947) jpbo-02
(FSDPPolicyWorkerBase pid=364946) cvbuff 0x400edfa4dc00 count 1024 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x4013ff800000 count 12582912 datatype 9 op 0
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount fc sendbuff 0x400eb9e1be00 recvbuf
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400fa2
(FSDPPolicyWorkerBase pid=364945) f 0x400eb9e1be00 count 4096 datatype 9 op 0 root 0 comm 0x400e615a9820 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400eb9e1ee00 count 32 datatype 9 op 0 root 0 comm 0x400e616c3ee0
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400edfa4f240 count 32 datatype 9 op 0 root 1 comm 0x400e06a9e080 [nranks=4] stream (n
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:36494
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:3649
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL IN
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL I
(FSDPPolicyWorkerBase pid=364944) FO Recv: opCount 0 sendbuff (nil) recvbuff 0x400e99e25400 count 32 datatype 9 op 0 root 0 comm 0x400e416cc220 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364945) INFO Broadcast: opCount 146 sendbuff 0x4010b2000000 recvbuff 0x4010b2000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] N
(FSDPPolicyWorkerBase pid=364947) NFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400e99e25400 count 32 datatype 9 op 0 root 0 comm 0x400e416caff0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364945) CCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400eb9e27e00 count 1024 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCou
(FSDPPolicyWorkerBase pid=364946) il)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-3
(FSDPPolicyWorkerBase pid=364945) nt 163 sendbuff 0x4010b2000000 recvbuff 0x4010b2000000 count 4194304 datatype 9 op 0 root 0 comm 0x400e615a9820 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 172 sendbuff 0x4010e0000000 recvbuff
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO Broadcast: opCount 18a sendbuff 0x4010e0000000 recvbuff 0x4010e0000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e415b1b60 [nranks=2] st
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO Broadcast: opCount 18a sendbuff 0x4010e0000000 recvbuff 0x4010e0000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e415b09a0 [nranks=2] s
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) t: opCount 26 sendbuff 0x400e9fa02a00 recvbuff 0x400e9fa02a00 count 128 datatype 9 op 0 root 0 comm 0x400dfa984d90 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil)
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442312 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x4010efa00000 count 12582912 datatype 9 op 0 root 0 comm 0x400e256ca1f0 [
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send:
(FSDPPolicyWorkerBase pid=364946) opCount 0 sendbuff (nil) recvbuff 0x400edfa542c0 count 32 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401367c00000 count 12582912 datatype 9 op 0 r
(AsyncVLLMInferenceEngine pid=316638, ip=10.128.25.28) (EngineCore_DP0 pid=317128) WARNING 06-12 01:01:36 [serial_utils.py:57] Allowing insecure serialization using pickle due to VLLM_ALLOW_INSECURE_SERIALIZATION=1
(AsyncVLLMInferenceEngine pid=316638, ip=10.128.25.28) (EngineCore_DP0 pid=317128) INFO 06-12 01:01:36 [vllm.py:690] Asynchronous scheduling is enabled.
(AsyncVLLMInferenceEngine pid=316638, ip=10.128.25.28) (EngineCore_DP0 pid=317128) WARNING 06-12 01:01:36 [vllm.py:735] Inductor compilation was disabled by user settings, optimizations settings that are only active during inductor compilation will be ignored.
(AsyncVLLMInferenceEngine pid=316638, ip=10.128.25.28) (EngineCore_DP0 pid=317128) INFO 06-12 01:01:36 [vllm.py:846] Cudagraph is disabled under eager mode
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x40137ac00000 count 4194304 datatype 9 op 0 root 3 comm 0x400dfaa9fd00 [nra
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) WARNING 06-12 01:01:37 [model.py:1350] Default vLLM sampling parameters have been overridden by the model's `generation_config.json`: `{'temperature': 0.6, 'top_k': 20, 'top_p': 0.95}`. If this is not intended, please relaunch vLLM instance with `--generation-config vllm`.
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) r
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) ecvbuff 0x4015d2200000 count 4194304 datatype 9 op 0 root 1 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(AsyncVLLMInferenceEngine pid=305555, ip=10.128.25.164) (EngineCore_DP0 pid=305972) INFO 06-12 01:01:35 [default_loader.py:293] Loading weights took 15.14 seconds [repeated 39x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x4013c5800000 count 1
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount e8 sendbuff 0x401626000000 recvbuf
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858
(AsyncVLLMInferenceEngine pid=305555, ip=10.128.25.164) (EngineCore_DP0 pid=305972) INFO 06-12 01:01:36 [gpu_model_runner.py:4222] Model loading took 15.27 GiB memory and 16.330888 seconds [repeated 39x across cluster]
(RolloutCoordinator pid=350242, ip=10.128.25.161) [fd-monitor] Started monitoring (every 120s)
(RolloutCoordinator pid=350242, ip=10.128.25.161) [fd-monitor] [01:01:44] OK: 46 / 131,072 FDs open (0.0% of soft limit, hard limit: 131,072)
(RolloutCoordinator pid=350242, ip=10.128.25.161) [fd-monitor] [01:01:44] OK: RSS 0.78 GiB | node mem 372.6/858.0 GiB used (43.4%), avail 485.4 GiB
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO cudaDriverVersion 13020 [repeated 7x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO NCCL version 2.27.7+cuda13.0 [repeated 7x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365455 [0] NCCL INFO NET/Plugin: Could not find: libnccl-net.so.  [repeated 7x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365455 [0] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_1:1/IB [2]mlx5_2:1/IB [3]mlx5_3:1/IB [RO]; OOB ib0:10.128.25.17<0> [repeated 7x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365455 [0] NCCL INFO Initialized NET plugin IB [repeated 7x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365512 [0] NCCL INFO Assigned NET plugin IB to comm [repeated 23x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365512 [0] NCCL INFO Using network IB [repeated 23x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365512 [0] NCCL INFO DMA-BUF is available on GPU device 0 [repeated 23x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365512 [0] NCCL INFO ncclCommInitRankConfig comm 0x400e616c3ee0 rank 3 nranks 4 cudaDev 0 nvmlDev 3 busId 3901000 commId 0xa71b72472f667c3e - Init START [repeated 23x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365455 [0] NCCL INFO RAS client listening socket at 127.0.0.1<28028> [repeated 7x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365455 [0] NCCL INFO NCCL_NET_GDR_LEVEL set by environment to LOC [repeated 7x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365512 [0] NCCL INFO Setting affinity for GPU 3 to 216-287 [repeated 23x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365512 [0] NCCL INFO NVLS multicast support is not available on dev 0 (NVLS_NCHANNELS 0) [repeated 15x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365512 [0] NCCL INFO comm 0x400e616c3ee0 rank 3 nRanks 4 nNodes 1 localRanks 4 localRank 3 MNNVL 0 [repeated 23x across cluster]
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365511 [0] NCCL INFO Channel 23/24 : 0 3 2 1 [repeated 168x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365512 [0] NCCL INFO Trees [0] -1/-1/-1->3->2 [1] -1/-1/-1->3->2 [2] -1/-1/-1->3->2 [3] -1/-1/-1->3->2 [4] -1/-1/-1->3->1 [5] -1/-1/-1->3->1 [6] -1/-1/-1->3->1 [7] -1/-1/-1->3->1 [8] 2/-1/-1->3->0 [9] 2/-1/-1->3->0 [10] 2/-1/-1->3->0 [11] 2/-1/-1->3->0 [12] -1/-1/-1->3->2 [13] -1/-1/-1->3->2 [14] -1/-1/-1->3->2 [15] -1/-1/-1->3->2 [16] -1/-1/-1->3->1 [17] -1/-1/-1->3->1 [18] -1/-1/-1->3->1 [19] -1/-1/-1->3->1 [20] 2/-1/-1->3->0 [21] 2/-1/-1->3->0 [22] 2/-1/-1->3->0 [23] 2/-1/-1->3->0 [repeated 23x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365512 [0] NCCL INFO P2P Chunksize set to 524288 [repeated 23x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365455 [0] NCCL INFO PROFILER/Plugin: Could not find: libnccl-profiler.so.  [repeated 7x across cluster]
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365511 [0] NCCL INFO Check P2P Type isAllDirectP2p 1 directMode 0 [repeated 5x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365516 [0] NCCL INFO [Proxy Service] Device 0 CPU core 274 [repeated 23x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365519 [0] NCCL INFO [Proxy Service UDS] Device 0 CPU core 276 [repeated 23x across cluster]
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442410 [0] NCCL INFO Channel 22/0 : 3[3] -> 2[2] via P2P/IPC [repeated 586x across cluster]
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365515 [0] NCCL INFO Allocated shareable buffer 0x401028200000 size 10485760 ipcDesc 0x400fd000ed30 [repeated 1175x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365523 [0] NCCL INFO [Proxy Progress] Device 0 CPU core 216 [repeated 23x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365494 [0] NCCL INFO Channel 39/0 : 0[3] -> 1[3] [receive] via NET/IB/3 [repeated 346x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365494 [0] NCCL INFO Channel 39/0 : 1[3] -> 0[3] [send] via NET/IB/3 [repeated 340x across cluster]
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365529 [0] NCCL INFO Imported shareable buffer device 0 size 2097152 ptr 0x40102aa00000 [repeated 1187x across cluster]
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442408 [0] NCCL INFO Connected all rings, use ring PXN 0 GDR 1 [repeated 23x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365512 [0] NCCL INFO Connected all trees [repeated 23x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365512 [0] NCCL INFO threadThresholds 8/8/64 | 32/8/64 | 512 | 512 [repeated 23x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365512 [0] NCCL INFO 24 coll channels, 24 collnet channels, 0 nvls channels, 32 p2p channels, 16 p2p channels per peer [repeated 23x across cluster]
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442349 [0] NCCL INFO TUNER/Plugin: Could not find: libnccl-tuner.so. Using internal tuner plugin. [repeated 7x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365512 [0] NCCL INFO ncclCommInitRankConfig comm 0x400e616c3ee0 rank 3 nranks 4 cudaDev 0 nvmlDev 3 busId 3901000 commId 0xa71b72472f667c3e - Init COMPLETE [repeated 22x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365512 [0] NCCL INFO Init timings - ncclCommInitRankConfig: rank 3 nranks 4 total 0.17 (kernels 0.00, alloc 0.00, bootstrap 0.00, allgathers 0.00, topo 0.02, graphs 0.01, connections 0.14, rest 0.00) [repeated 23x across cluster]
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365511 [0] NCCL INFO CC Off, workFifoBytes 1048576 [repeated 5x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount 186 sendbuff 0x400e9fa02a00 recvbuff 0x400e9fa02a00 count 128 datatype 9 op 0 root 0 comm 0x400dfa984d90 [nranks=2] stream (nil) [repeated 5447x across cluster]
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442390 [0] NCCL INFO Channel 01/0 : 0[2] -> 1[2] [se
(AsyncVLLMInferenceEngine pid=305555, ip=10.128.25.164) (EngineCore_DP0 pid=305972) INFO 06-12 01:01:38 [gpu_worker.py:373] Available KV cache memory: 49.32 GiB [repeated 39x across cluster]
(AsyncVLLMInferenceEngine pid=305555, ip=10.128.25.164) (EngineCore_DP0 pid=305972) INFO 06-12 01:01:38 [kv_cache_utils.py:1307] GPU KV cache size: 359,120 tokens [repeated 39x across cluster]
(AsyncVLLMInferenceEngine pid=305555, ip=10.128.25.164) (EngineCore_DP0 pid=305972) INFO 06-12 01:01:38 [kv_cache_utils.py:1312] Maximum concurrency for 32,768 tokens per request: 10.96x [repeated 39x across cluster]
(FSDPPolicyWorkerBase pid=364944) jpbo [repeated 2x across cluster]
(AsyncVLLMInferenceEngine pid=305555, ip=10.128.25.164) (EngineCore_DP0 pid=305972) INFO 06-12 01:01:39 [kernel_warmup.py:44] Skipping FlashInfer autotune because it is disabled. [repeated 39x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365494 [0] NCCL INFO Connected binomial trees [repeated 7x across cluster]
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) nd] via NET/IB/2
(AsyncVLLMInferenceEngine pid=305555, ip=10.128.25.164) (EngineCore_DP0 pid=305972) INFO 06-12 01:01:39 [core.py:278] init engine (profile, create kv cache, warmup model) took 3.08 seconds [repeated 39x across cluster]
(FSDPPolicyWorkerBase pid=364945) jp
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442310 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x4010d8200000 count 4194304 datatype 9 op 0 root 0 comm 0x400e096cb190 [nranks=4] stream (nil) [repeated 2329x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400e9fa02ac0 count 32 datatype 9 op 0 root 3 comm 0x400dfaa9fd00 [nranks=4] stream (nil) [repeated 1758x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount a sendbuff 0x401103000000 recvbuff 0x401103000000 count 4194304 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 14x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount b sendbuff 0x401135400000 recvbuff 0x401135400000 count 16777216 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 14x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount c sendbuff 0x401107800000 recvbuff 0x401107800000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 24x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount d sendbuff 0x401107800000 recvbuff 0x401107800000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 14x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount e sendbuff 0x401107800000 recvbuff 0x401107800000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 14x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount f sendbuff 0x401107800000 recvbuff 0x401107800000 count 16777216 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 24x across cluster]
(FSDPPolicyWorkerBase pid=364947) (nil) recvbuff 0x400eae800000 count 12582912 datatype 9 op 0 root 0 comm 0x400e416caff0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount aa sendbuff 0x4013a0000000 recvbuff 0x4013a0000000 count 4194304 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 14x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount ab sendbuff 0x4013a0000000 recvbuff 0x4013a0000000 count 4194304 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 14x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount ac sendbuff 0x4013a0000000 recvbuff 0x4013a0000000 count 16777216 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 14x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount ad sendbuff 0x4013a6000000 recvbuff 0x4013a6000000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 22x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount ae sendbuff 0x4013a6000000 recvbuff 0x4013a6000000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 14x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount af sendbuff 0x4013a6000000 recvbuff 0x4013a6000000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 14x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x4013af000
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) 000 count 12582912 datatype 9 op 0 root 2 comm 0x400dfaa9fd00 [nranks=4] stream (nil) [repeated 5x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount ba sendbuff 0x4013ac000000 recvbuff 0x4013ac000000 count 16777216 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 15x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount bb sendbuff 0x4013ac000000 recvbuff 0x4013ac000000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 27x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount bc sendbuff 0x4013ac000000 recvbuff 0x4013ac000000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 15x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount bd sendbuff 0x4013ac000000 recvbuff 0x4013ac000000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 15x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount be sendbuff 0x4013ac000000 recvbuff 0x4013ac000000 count 16777216 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 27x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount bf sendbuff 0x4013ac000000 recvbuff 0x4013ac000000 count 4194304 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 15x across cluster]
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO Broadcast: opCount 15e sendbuff 0x401 [repeated 4x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount ca sendbuff 0x4013b5000000 recvbuff 0x4013b5000000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 15x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount cb sendbuff 0x4013b5000000 recvbuff 0x4013b5000000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 15x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 128 sendbuff 0x400eb9e20e00 recvbuff 0x400eb9e20e00 count 4096 datatype 9 op 0 root 0 comm 0x400e615a [repeated 8x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) recvbuff 0x40134c400000 count 12582912 datatype 9 op 0 root 1 comm 0x400dfaa9fd00 [nranks=4] stream (nil) [repeated 5x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) nks=4] stream (nil) [repeated 14x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 95 sendbuff 0x400eb9e10200 recvbuff 0x400eb9e10200 count 128 datatype
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount cc sendbuff 0x4013b5000000 recvbuff 0x4013b5000000 count 16777216 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 27x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount cd sendbuff 0x4013b5000000 recvbuff 0x4013b5000000 count 4194304 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 15x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount ce sendbuff 0x4013b5000000 recvbuff 0x4013b5000000 count 4194304 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 15x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount cf sendbuff 0x4013b5c00000 recvbuff 0x4013b5c00000 count 16777216 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 15x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount da sendbuff 0x401620000000 recvbuff 0x401620000000 count 16777216 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 27x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount db sendbuff 0x4013c6800000 recvbuff 0x4013c6800000 count 4194304 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 15x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount dc sendbuff 0x4013c6800000 recvbuff 0x4013c6800000 count 4194304 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 15x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount dd sendbuff 0x401620400000 recvbuff 0x401620400000 count 16777216 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 15x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount de sendbuff 0x401626000000 recvbuff 0x401626000000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 27x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount df sendbuff 0x401626000000 recvbuff 0x401626000000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 15x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount ea sendbuff 0x401626000000 recvbuff 0x401626000000 count 4194304 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 15x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount eb sendbuff 0x401628800000 recvbuff 0x401628800000 count 16777216 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 15x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount ec sendbuff 0x401630800000 recvbuff 0x401630800000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 27x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount ed sendbuff 0x401630800000 recvbuff 0x401630800000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 15x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount ee sendbuff 0x401630800000 recvbuff 0x401630800000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 15x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount ef sendbuff 0x401630800000 recvbuff 0x401630800000 count 16777216 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 27x across cluster]
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO Broadcast: opCount e9 sendbuff 0x4010a4000000 recvbuff 0x4010a4000000 count 4194 [repeated 6x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) 2582912 datatype 9 op 0 root 3 comm 0x400dfaa9fd00 [nranks=4] stream (nil) [repeated 7x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount fa sendbuff 0x400e9fa02a00 recvbuff 0x400e9fa02a00 count 128 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil) [repeated 20x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount fb sendbuff 0x4015d1a00000 recvbuff 0x4015d1a00000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa984d90 [nranks=2] stream (nil) [repeated 12x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount fc sendbuff 0x400e9fa4b400 recvbuff 0x400e9fa4b400 count 4096 datatype 9 op 0 root 0 comm 0x400dfa984d90 [nranks=2] stream (nil) [repeated 10x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount fd sendbuff 0x400e9fa4b400 recvbuff 0x400e9fa4b400 count 4096 datatype 9 op 0 root 0 comm 0x400dfa984d90 [nranks=2] stream (nil) [repeated 9x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount fe sendbuff 0x4015d1a00000 recvbuff 0x4015d1a00000 count 16777216 datatype 9 op 0 root 0 comm 0x400dfa984d90 [nranks=2] stream (nil) [repeated 9x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount ff sendbuff 0x4015d1a00000 recvbuff 0x4015d1a00000 count 4194304 datatype 9 op 0 root 0 comm 0x400dfa984d90 [nranks=2] stream (nil) [repeated 9x across cluster]
(FSDPPolicyWorkerBase pid=364946) root 1 comm 0x400e06a9e080 [nranks=4] stream (nil) [repeated 3x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) oot 2 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400e99e2a400 count 32 datatype 9 op 0 root 0 comm 0x400e41 [repeated 2x across cluster]
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO Broadcast: opCount a8
(FSDPPolicyWorkerBase pid=364944) sendbuff 0x4010a0000000 recvbuff 0x4010a0000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e412e4700 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) vbuff 0x400eb9e15200 count 128 datatype 9 op 0 root 0 comm 0x400e615a9820 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO Broadcast: opCount ad sendbuff 0x401034e00000 recvbuff 0x401034e00000 count 50331648 datatype 9 op 0
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) 9 op 0 root 0 comm 0x400e092e33d0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400eb9e2c
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) f 0x401626000000 count 16777216 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442310 [0] NCCL  [repeated 2x across cluster]
(AsyncVLLMInferenceEngine pid=305427, ip=10.128.25.164) (EngineCore_DP0 pid=305964) WARNING 06-12 01:01:39 [serial_utils.py:57] Allowing insecure serialization using pickle due to VLLM_ALLOW_INSECURE_SERIALIZATION=1 [repeated 39x across cluster]
(AsyncVLLMInferenceEngine pid=305427, ip=10.128.25.164) (EngineCore_DP0 pid=305964) INFO 06-12 01:01:39 [vllm.py:690] Asynchronous scheduling is enabled. [repeated 39x across cluster]
(AsyncVLLMInferenceEngine pid=305427, ip=10.128.25.164) (EngineCore_DP0 pid=305964) WARNING 06-12 01:01:39 [vllm.py:735] Inductor compilation was disabled by user settings, optimizations settings that are only active during inductor compilation will be ignored. [repeated 39x across cluster]
(AsyncVLLMInferenceEngine pid=305427, ip=10.128.25.164) (EngineCore_DP0 pid=305964) INFO 06-12 01:01:39 [vllm.py:846] Cudagraph is disabled under eager mode [repeated 39x across cluster]
(AsyncVLLMInferenceEngine pid=305554, ip=10.128.25.164) WARNING 06-12 01:01:39 [model.py:1350] Default vLLM sampling parameters have been overridden by the model's `generation_config.json`: `{'temperature': 0.6, 'top_k': 20, 'top_p': 0.95}`. If this is not intended, please relaunch vLLM instance with `--generation-config vllm`. [repeated 39x across cluster]
(RolloutCoordinator pid=479438, ip=10.128.25.176) [fd-monitor] Started monitoring (every 120s)
(RolloutCoordinator pid=479438, ip=10.128.25.176) [fd-monitor] [01:01:51] OK: 46 / 131,072 FDs open (0.0% of soft limit, hard limit: 131,072)
(RolloutCoordinator pid=479438, ip=10.128.25.176) [fd-monitor] [01:01:51] OK: RSS 0.78 GiB | node mem 359.9/858.0 GiB used (41.9%), avail 498.1 GiB
(RolloutCoordinator pid=301361, ip=10.128.25.162) [fd-monitor] Started monitoring (every 120s)
(RolloutCoordinator pid=301361, ip=10.128.25.162) [fd-monitor] [01:01:58] OK: 46 / 131,072 FDs open (0.0% of soft limit, hard limit: 131,072)
(RolloutCoordinator pid=301361, ip=10.128.25.162) [fd-monitor] [01:01:58] OK: RSS 0.78 GiB | node mem 371.0/858.0 GiB used (43.2%), avail 486.9 GiB
(RolloutCoordinator pid=380389, ip=10.128.25.25) [fd-monitor] Started monitoring (every 120s)
(RolloutCoordinator pid=380389, ip=10.128.25.25) [fd-monitor] [01:02:07] OK: 46 / 131,072 FDs open (0.0% of soft limit, hard limit: 131,072) [repeated 2x across cluster]
(RolloutCoordinator pid=380389, ip=10.128.25.25) [fd-monitor] [01:02:07] OK: RSS 0.78 GiB | node mem 381.1/858.0 GiB used (44.4%), avail 476.9 GiB [repeated 2x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) [rank-0]: Loading model from /e/data1/datasets/playground/ot-baf/explore-tis-untrunc/explore-tis-untrunc/checkpoints/global_step_82/policy/model_world_size_8_rank_0.pt
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) [rank-0]: Loading extra_state from /e/data1/datasets/playground/ot-baf/explore-tis-untrunc/explore-tis-untrunc/checkpoints/global_step_82/policy/extra_state_world_size_8_rank_0.pt
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) [rank-0]: Loading optim from /e/data1/datasets/playground/ot-baf/explore-tis-untrunc/explore-tis-untrunc/checkpoints/global_step_82/policy/optim_world_size_8_rank_0.pt
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) [rank-0]: Successfully loaded model state dict
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) [rank-0]: Successfully loaded optimizer state
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) [rank-0]: Successfully loaded scheduler state
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) [rank-0]: Checkpoint loaded successfully from /e/data1/datasets/playground/ot-baf/explore-tis-untrunc/explore-tis-untrunc/checkpoints/global_step_82/policy
(FSDPPolicyWorkerBase pid=364945) e00 count 1024 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 181 sendbuff 0x400eb9e2d600 recvbuff 0x400eb9e2d600 count 4096 datatype 9 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 181 sendbuff 0x400eb9e2d600 recvbuff 0x400eb9e2d600 count 4096 datatype 9 op 0 root 0 comm 0x400e615a9820 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400eb9e2ae00 count 1024 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 182 sendbuff 0x4010ec000000 recvbuff 0x4010ec000000 count 16777216 datatype 9 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 182 sendbuff 0x4010ec000000 recvbuff 0x4010ec000000 count 16777216 datatype 9 op 0 root 0 comm 0x400e615a9820 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x4010e5000000 count 4194304 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 183 sendbuff 0x4010e5800000 recvbuff 0x4010e5800000 count 4194304 datatype 9 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 183 sendbuff 0x4010e5800000 recvbuff 0x4010e5800000 count 4194304 datatype 9 op 0 root 0 comm 0x400e615a9820 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x4010ec000000 count 1048576 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 184 sendbuff 0x4010ec200000 recvbuff 0x4010ec200000 count 4194304 datatype 9 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 184 sendbuff 0x4010ec200000 recvbuff 0x4010ec200000 count 4194304 datatype 9 op 0 root 0 comm 0x400e615a9820 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x4010e5800000 count 1048576 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 185 sendbuff 0x4010eca00000 recvbuff 0x4010eca00000 count 16777216 datatype 9 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 185 sendbuff 0x4010eca00000 recvbuff 0x4010eca00000 count 16777216 datatype 9 op 0 root 0 comm 0x400e615a9820 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x4010ec200000 count 4194304 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 186 sendbuff 0x400eb9e2b600 recvbuff 0x400eb9e2b600 count 128 datatype 9 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 186 sendbuff 0x400eb9e2b600 recvbuff 0x400eb9e2b600 count 128 datatype 9 op 0 root 0 comm 0x400e615a9820 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400eb9e2b800 count 32 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 187 sendbuff 0x400eb9e2ba00 recvbuff 0x400eb9e2ba00 count 128 datatype 9 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 187 sendbuff 0x400eb9e2ba00 recvbuff 0x400eb9e2ba00 count 128 datatype 9 op 0 root 0 comm 0x400e615a9820 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400eb9e2b600 count 32 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 188 sendbuff 0x4010f2000000 recvbuff 0x4010f2000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 188 sendbuff 0x4010f2000000 recvbuff 0x4010f2000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e615a9820 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x4010eca00000 count 12582912 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 189 sendbuff 0x4010f8000000 recvbuff 0x4010f8000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 189 sendbuff 0x4010f8000000 recvbuff 0x4010f8000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e615a9820 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x4010ee200000 count 12582912 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 18a sendbuff 0x4010f2000000 recvbuff 0x4010f2000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 18a sendbuff 0x4010f2000000 recvbuff 0x4010f2000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e615a9820 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x4010efa00000 count 12582912 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 18b sendbuff 0x400eb9e2d600 recvbuff 0x400eb9e2d600 count 4096 datatype 9 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 18b sendbuff 0x400eb9e2d600 recvbuff 0x400eb9e2d600 count 4096 datatype 9 op 0 root 0 comm 0x400e615a9820 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400eb9e2ba00 count 1024 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 18c sendbuff 0x400eb9e2f600 recvbuff 0x400eb9e2f600 count 4096 datatype 9 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 18c sendbuff 0x400eb9e2f600 recvbuff 0x400eb9e2f600 count 4096 datatype 9 op 0 root 0 comm 0x400e615a9820 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400eb9e2c200 count 1024 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 18d sendbuff 0x400eb9e2d600 recvbuff 0x400eb9e2d600 count 4096 datatype 9 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 18d sendbuff 0x400eb9e2d600 recvbuff 0x400eb9e2d600 count 4096 datatype 9 op 0 root 0 comm 0x400e615a9820 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400eb9e2f600 count 1024 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 18e sendbuff 0x401100000000 recvbuff 0x401100000000 count 622329856 datatype 9 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Broadcast: opCount 18e sendbuff 0x401100000000 recvbuff 0x401100000000 count 622329856 datatype 9 op 0 root 0 comm 0x400e615a9820 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x40114a400000 count 155582464 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO AllReduce: opCount 18f sendbuff 0x400eb9e88e00 recvbuff 0x400eb9e88e00 count 1 datatype 7 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO AllReduce: opCount 18f sendbuff 0x400eb9e88c00 recvbuff 0x400eb9e88c00 count 1 datatype
(RolloutCoordinator pid=350242, ip=10.128.25.161) [fd-monitor] [01:03:44] OK: 47 / 131,072 FDs open (0.0% of soft limit, hard limit: 131,072)
(RolloutCoordinator pid=350242, ip=10.128.25.161) [fd-monitor] [01:03:44] OK: RSS 0.89 GiB | node mem 372.8/858.0 GiB used (43.4%), avail 485.2 GiB
(RolloutCoordinator pid=479438, ip=10.128.25.176) [fd-monitor] [01:03:51] OK: 47 / 131,072 FDs open (0.0% of soft limit, hard limit: 131,072)
(RolloutCoordinator pid=479438, ip=10.128.25.176) [fd-monitor] [01:03:51] OK: RSS 0.89 GiB | node mem 360.2/858.0 GiB used (42.0%), avail 497.8 GiB
(RolloutCoordinator pid=301361, ip=10.128.25.162) [fd-monitor] [01:03:58] OK: 47 / 131,072 FDs open (0.0% of soft limit, hard limit: 131,072)
(RolloutCoordinator pid=301361, ip=10.128.25.162) [fd-monitor] [01:03:58] OK: RSS 0.89 GiB | node mem 371.2/858.0 GiB used (43.3%), avail 486.8 GiB
(RolloutCoordinator pid=380389, ip=10.128.25.25) [fd-monitor] [01:04:07] OK: 47 / 131,072 FDs open (0.0% of soft limit, hard limit: 131,072) [repeated 2x across cluster]
(RolloutCoordinator pid=380389, ip=10.128.25.25) [fd-monitor] [01:04:07] OK: RSS 0.89 GiB | node mem 381.3/858.0 GiB used (44.4%), avail 476.7 GiB [repeated 2x across cluster]
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985) INFO 06-12 01:04:59 [worker_base.py:289] Injected <class 'skyrl_train.inference_engines.vllm.vllm_engine.WorkerWrap'> into <class 'vllm.v1.worker.gpu_worker.Worker'> for extended collective_rpc calls ['_apply_fp8_weight_loader_patches', '_is_fp8_model', '_quantize_weights_for_fp8', '_restore_param_subclasses', '_undo_param_subclasses', 'begin_weight_update', 'destroy_weights_update_group', 'end_weight_update', 'init_weight_update_communicator', 'load_weights', 'read_named_weights', 'set_numa_affinity', 'test_rpc']
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985) INFO 06-12 01:05:00 [parallel_state.py:1234] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://10.128.25.165:33847 backend=nccl
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985) INFO 06-12 01:05:00 [parallel_state.py:1445] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank N/A
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985) INFO 06-12 01:05:02 [gpu_model_runner.py:4125] Starting to load model /e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6...
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985) INFO 06-12 01:05:04 [cuda.py:367] Using FLASH_ATTN attention backend out of potential backends: ['FLASH_ATTN', 'FLASHINFER', 'TRITON_ATTN', 'FLEX_ATTENTION'].
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985) INFO 06-12 01:05:19 [default_loader.py:293] Loading weights took 15.15 seconds
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986) INFO 06-12 01:04:59 [worker_base.py:289] Injected <class 'skyrl_train.inference_engines.vllm.vllm_engine.WorkerWrap'> into <class 'vllm.v1.worker.gpu_worker.Worker'> for extended collective_rpc calls ['_apply_fp8_weight_loader_patches', '_is_fp8_model', '_quantize_weights_for_fp8', '_restore_param_subclasses', '_undo_param_subclasses', 'begin_weight_update', 'destroy_weights_update_group', 'end_weight_update', 'init_weight_update_communicator', 'load_weights', 'read_named_weights', 'set_numa_affinity', 'test_rpc'] [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986) INFO 06-12 01:05:00 [parallel_state.py:1234] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://10.128.25.165:34269 backend=nccl [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986) INFO 06-12 01:05:00 [parallel_state.py:1445] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank N/A [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986) INFO 06-12 01:05:02 [gpu_model_runner.py:4125] Starting to load model /e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6... [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986) INFO 06-12 01:05:04 [cuda.py:367] Using FLASH_ATTN attention backend out of potential backends: ['FLASH_ATTN', 'FLASHINFER', 'TRITON_ATTN', 'FLEX_ATTENTION']. [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985) INFO 06-12 01:05:20 [gpu_model_runner.py:4222] Model loading took 15.27 GiB memory and 17.668826 seconds
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985) INFO 06-12 01:05:23 [gpu_worker.py:373] Available KV cache memory: 49.32 GiB
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985) INFO 06-12 01:05:23 [kv_cache_utils.py:1307] GPU KV cache size: 359,120 tokens
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985) INFO 06-12 01:05:23 [kv_cache_utils.py:1312] Maximum concurrency for 32,768 tokens per request: 10.96x
(AsyncVLLMInferenceEngine pid=304566, ip=10.128.25.165) (EngineCore_DP0 pid=304984) INFO 06-12 01:05:24 [kernel_warmup.py:44] Skipping FlashInfer autotune because it is disabled.
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985) INFO 06-12 01:05:24 [core.py:278] init engine (profile, create kv cache, warmup model) took 4.09 seconds
(AsyncVLLMInferenceEngine pid=304568, ip=10.128.25.165) (EngineCore_DP0 pid=304987) WARNING 06-12 01:05:24 [serial_utils.py:57] Allowing insecure serialization using pickle due to VLLM_ALLOW_INSECURE_SERIALIZATION=1
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986) INFO 06-12 01:05:19 [default_loader.py:293] Loading weights took 15.15 seconds [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985) INFO 06-12 01:05:24 [vllm.py:690] Asynchronous scheduling is enabled.
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985) WARNING 06-12 01:05:24 [vllm.py:735] Inductor compilation was disabled by user settings, optimizations settings that are only active during inductor compilation will be ignored.
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) (EngineCore_DP0 pid=304985) INFO 06-12 01:05:24 [vllm.py:846] Cudagraph is disabled under eager mode
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) WARNING 06-12 01:05:25 [model.py:1350] Default vLLM sampling parameters have been overridden by the model's `generation_config.json`: `{'temperature': 0.6, 'top_k': 20, 'top_p': 0.95}`. If this is not intended, please relaunch vLLM instance with `--generation-config vllm`.
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) :441948 [0] NCCL INFO Broadcast: opCount 187 sendbuff 0x400e9fa02a00 recvbuff 0x400e9fa02a00 count 128 datatype 9 op 0 root 0 comm 0x400dfa984d90 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400e9fa02a40 count 32 datatype 9 op 0 root 1 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400e9fa02a80 count 32 datatype 9 op 0 root 2 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400e9fa02ac0 count 32 datatype 9 op 0 root 3 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount fa sendbuff 0x401640000000 recvbuff 0x401640000000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount 188 sendbuff 0x401640000000 recvbuff 0x401640000000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa984d90 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401641800000 count 12582912 datatype 9 op 0 root 1 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401643000000 count 12582912 datatype 9 op 0 root 2 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401644800000 count 12582912 datatype 9 op 0 root 3 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount fb sendbuff 0x401640000000 recvbuff 0x401640000000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount 189 sendbuff 0x401640000000 recvbuff 0x401640000000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa984d90 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401641800000 count 12582912 datatype 9 op 0 root 1 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401643000000 count 12582912 datatype 9 op 0 root 2 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401644800000 count 12582912 datatype 9 op 0 root 3 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount fc sendbuff 0x401640000000 recvbuff 0x401640000000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount 18a sendbuff 0x401640000000 recvbuff 0x401640000000 count 50331648 datatype 9 op 0 root 0 comm 0x400dfa984d90 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401641800000 count 12582912 datatype 9 op 0 root 1 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401643000000 count 12582912 datatype 9 op 0 root 2 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401644800000 count 12582912 datatype 9 op 0 root 3 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount fd sendbuff 0x400e9fa5a400 recvbuff 0x400e9fa5a400 count 4096 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount 18b sendbuff 0x400e9fa5a400 recvbuff 0x400e9fa5a400 count 4096 datatype 9 op 0 root 0 comm 0x400dfa984d90 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400e9fa5ac00 count 1024 datatype 9 op 0 root 1 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400e9fa5b400 count 1024 datatype 9 op 0 root 2 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400e9fa5bc00 count 1024 datatype 9 op 0 root 3 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount fd sendbuff 0x400e9fa5a400 recvbuff 0x400e9fa5a400 count 4096 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount 18c sendbuff 0x400e9fa5a400 recvbuff 0x400e9fa5a400 count 4096 datatype 9 op 0 root 0 comm 0x400dfa984d90 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400e9fa5ac00 count 1024 datatype 9 op 0 root 1 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400e9fa5b400 count 1024 datatype 9 op 0 root 2 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400e9fa5bc00 count 1024 datatype 9 op 0 root 3 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount fd sendbuff 0x400e9fa5a400 recvbuff 0x400e9fa5a400 count 4096 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount 18d sendbuff 0x400e9fa5a400 recvbuff 0x400e9fa5a400 count 4096 datatype 9 op 0 root 0 comm 0x400dfa984d90 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400e9fa5ac00 count 1024 datatype 9 op 0 root 1 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400e9fa5b400 count 1024 datatype 9 op 0 root 2 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x400e9fa5bc00 count 1024 datatype 9 op 0 root 3 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount fd sendbuff 0x401660000000 recvbuff 0x401660000000 count 622329856 datatype 9 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Broadcast: opCount 18e sendbuff 0x401660000000 recvbuff 0x401660000000 count 622329856 datatype 9 op 0 root 0 comm 0x400dfa984d90 [nranks=2] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x4016728c0000 count 155582464 datatype 9 op 0 root 1 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401685180000 count 155582464 datatype 9 op 0 root 2 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x401697a40000 count 155582464 datatype 9 op 0 root 3 comm 0x400dfaa9fd00 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e9fa88e00 recvbuff 0x400e9fa88e00 count 1 datatype 7 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil)
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:301668 [0] NCCL INFO cudaDriverVersion 13020
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:301668 [0] NCCL INFO NCCL version 2.27.7+cuda13.0
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO NET/Plugin: Could not find: libnccl-net.so.
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_1:1/IB [2]mlx5_2:1/IB [3]mlx5_3:1/IB [RO]; OOB ib0:10.128.25.163<0>
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Initialized NET plugin IB
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Assigned NET plugin IB to comm
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Using network IB
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO DMA-BUF is available on GPU device 0
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO ncclCommInitRankConfig comm 0xaaab0c759090 rank 25 nranks 49 cudaDev 0 nvmlDev 0 busId 901000 commId 0xa8aa92223a1db3f3 - Init START
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO RAS client listening socket at 127.0.0.1<28028>
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO NCCL_NET_GDR_LEVEL set by environment to LOC
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Setting affinity for GPU 0 to 0-71
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO NVLS multicast support is not available on dev 0 (NVLS_NCHANNELS 0)
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO comm 0xaaab0c759090 rank 25 nRanks 49 nNodes 13 localRanks 4 localRank 0 MNNVL 0
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Trees [0] 38/-1/-1->25->21 [1] -1/-1/-1->25->40 [2] 38/-1/-1->25->39 [3] 39/-1/-1->25->40 [4] 38/21/26->25->17 [5] -1/-1/-1->25->40 [6] 38/-1/-1->25->39 [7] 39/-1/-1->25->40
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO P2P Chunksize set to 131072
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO PROFILER/Plugin: Could not find: libnccl-profiler.so.
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO [Proxy Service] Device 0 CPU core 24
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302095 [0] NCCL INFO [Proxy Service UDS] Device 0 CPU core 25
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302099 [0] NCCL INFO [Proxy Progress] Device 0 CPU core 26
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 00/0 : 25[0] -> 26[0] [send] via NET/IB/0
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 04/0 : 25[0] -> 26[0] [send] via NET/IB/0
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 01/0 : 21[0] -> 25[0] [receive] via NET/IB/0
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 05/0 : 21[0] -> 25[0] [receive] via NET/IB/0
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 01/0 : 25[0] -> 38[1] via P2P/IPC
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x401790800000 size 2097152 ipcDesc 0x40096400ae40
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 05/0 : 25[0] -> 38[1] via P2P/IPC
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x401790a00000 size 2097152 ipcDesc 0x40096400bc60
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 02/0 : 25[0] -> 40[3] via P2P/IPC
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x401790c00000 size 2097152 ipcDesc 0x40096400ca30
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 03/0 : 25[0] -> 40[3] via P2P/IPC
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x401790e00000 size 2097152 ipcDesc 0x40096400d800
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 06/0 : 25[0] -> 40[3] via P2P/IPC
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x401791000000 size 2097152 ipcDesc 0x40096400e5d0
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 07/0 : 25[0] -> 40[3] via P2P/IPC
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x401791200000 size 2097152 ipcDesc 0x40096400f3a0
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x401791400000 size 10485760 ipcDesc 0x400964010170
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x401791e00000 size 10485760 ipcDesc 0x400964010f40
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x401792800000 size 10485760 ipcDesc 0x400964010f40
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x401793200000 size 10485760 ipcDesc 0x400964010f40
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x401793c00000 size 10485760 ipcDesc 0x400964010f40
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x401794600000 size 10485760 ipcDesc 0x400964010f40
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Imported shareable buffer device 0 size 10485760 ptr 0x401795000000
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Imported shareable buffer device 0 size 10485760 ptr 0x401795a00000
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Imported shareable buffer device 0 size 10485760 ptr 0x401796400000
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Imported shareable buffer device 0 size 10485760 ptr 0x401796e00000
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Imported shareable buffer device 0 size 10485760 ptr 0x401797800000
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Imported shareable buffer device 0 size 10485760 ptr 0x401798200000
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Imported shareable buffer device 0 size 2097152 ptr 0x401798c00000
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Imported shareable buffer device 0 size 2097152 ptr 0x401798e00000
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Imported shareable buffer device 0 size 2097152 ptr 0x401799000000
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Imported shareable buffer device 0 size 2097152 ptr 0x401799200000
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Imported shareable buffer device 0 size 2097152 ptr 0x401799400000
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Imported shareable buffer device 0 size 2097152 ptr 0x401799600000
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Connected all rings, use ring PXN 0 GDR 0
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 00/0 : 21[0] -> 25[0] [receive] via NET/IB/0
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 04/0 : 21[0] -> 25[0] [receive] via NET/IB/0
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 04/0 : 17[0] -> 25[0] [receive] via NET/IB/0
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 00/0 : 25[0] -> 38[1] via P2P/IPC
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x401799800000 size 2097152 ipcDesc 0x400964016140
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 02/0 : 25[0] -> 38[1] via P2P/IPC
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x401799a00000 size 2097152 ipcDesc 0x400964016140
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 04/0 : 25[0] -> 38[1] via P2P/IPC
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x401799c00000 size 2097152 ipcDesc 0x400964016140
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 06/0 : 25[0] -> 38[1] via P2P/IPC
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x401799e00000 size 2097152 ipcDesc 0x400964016140
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 02/0 : 25[0] -> 39[2] via P2P/IPC
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x40179a000000 size 2097152 ipcDesc 0x400964016140
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 03/0 : 25[0] -> 39[2] via P2P/IPC
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x40179a200000 size 2097152 ipcDesc 0x400964016140
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 06/0 : 25[0] -> 39[2] via P2P/IPC
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x40179a400000 size 2097152 ipcDesc 0x400964016140
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 07/0 : 25[0] -> 39[2] via P2P/IPC
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x40179a600000 size 2097152 ipcDesc 0x400964016140
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 01/0 : 25[0] -> 40[3] via P2P/IPC
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x40179a800000 size 2097152 ipcDesc 0x400964016140
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302065 [0] NCCL INFO Channel 05/0 : 25[0] -> 40[3] via P2P/IPC
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x40179aa00000 size 2097152 ipcDesc 0x400964016140
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x40179ac00000 size 10485760 ipcDesc 0x400964016140
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x40179b600000 size 10485760 ipcDesc 0x400964016140
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-029-35:301668:302091 [0] NCCL INFO Allocated shareable buffer 0x40179c000000 size 10485760 ipcDesc 0x400964016140
(AsyncVLLMInferenceEngine pid=301117, ip=10.128.25.163) jpbo-0
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986) INFO 06-12 01:05:20 [gpu_model_runner.py:4222] Model loading took 15.27 GiB memory and 17.667732 seconds [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986) INFO 06-12 01:05:23 [gpu_worker.py:373] Available KV cache memory: 49.32 GiB [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986) INFO 06-12 01:05:23 [kv_cache_utils.py:1307] GPU KV cache size: 359,120 tokens [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986) INFO 06-12 01:05:23 [kv_cache_utils.py:1312] Maximum concurrency for 32,768 tokens per request: 10.96x [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=301250, ip=10.128.25.163) jpb
(AsyncVLLMInferenceEngine pid=315936, ip=10.128.25.23) jpbo-026-39:316481:316921 [0] NCCL INFO Allocated shareable buffer 0x4017bd000000
(AsyncVLLMInferenceEngine pid=349371, ip=10.128.25.161) jpbo-029-33:349999:350525 [0] NCCL INFO Allocated shareable buffer 0x4017bc600000 size 1
(AsyncVLLMInferenceEngine pid=316064, ip=10.128.25.23) jpbo-026-39:316471:316887 [0] NCCL INFO Channel 00/0 : 4[2] ->
(AsyncVLLMInferenceEngine pid=349499, ip=10.128.25.161) jpbo-029
(AsyncVLLMInferenceEngine pid=316063, ip=10.128.25.23) jpbo-026-39:316483:316889 [0] NCCL INFO Channel 00/0
(AsyncVLLMInferenceEngine pid=349500, ip=10.128.25.161) jpbo-029-33:349997:35
(AsyncVLLMInferenceEngine pid=349498, ip=10.128.25.161) jp
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) jpbo-026-39:316475:3
(AsyncVLLMInferenceEngine pid=300569, ip=10.128.25.162) jpbo-
(AsyncVLLMInferenceEngine pid=300697, ip=10.128.25.162) jpbo-0
(AsyncVLLMInferenceEngine pid=316510, ip=10.128.25.28) jpbo-026-44:317118:317547 [0] NCCL INFO Allocat
(AsyncVLLMInferenceEngine pid=316638, ip=10.128.25.28) jpbo-02
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) jpbo-0
(AsyncVLLMInferenceEngine pid=304568, ip=10.128.25.165) jpbo-0
(AsyncVLLMInferenceEngine pid=478659, ip=10.128.25.176) jpbo-029-48:479197:4
(AsyncVLLMInferenceEngine pid=478789, ip=10.128.25.176) jpbo-029-48:479189:479707 [0] NCCL INFO Allocated shareable buffer 0x4017bfc00000 size 2097152 ipcDes
(AsyncVLLMInferenceEngine pid=478791, ip=10.128.25.176) jpbo-029-48:47919
(AsyncVLLMInferenceEngine pid=478790, ip=10.128.25.176) jpbo-029-48:479185:479704 [0] NCCL INFO Allocated shareable buffer 0x40179e200000 s
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) jpbo-026-43:326772:327159 [0] NCCL INFO Imported shareable buffer de
(AsyncVLLMInferenceEngine pid=249097, ip=10.128.25.24) jpbo-026-40:249632:250073 [0] NCCL INFO Allocated
(AsyncVLLMInferenceEngine pid=249227, ip=10.128.25.24) jpbo-02
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) jpbo-026-41:380145:380620 [0] NCCL INFO Connected all trees
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) jpbo-026-41:380145:380620 [0] NCCL INFO threadThresholds 8/8/64 | 392/8/64 | 512 | 512
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) jpbo-026-41:380145:380620 [0] NCCL INFO 8 coll channels, 8 collnet channels, 0 nvls channels, 8 p2p channels, 1 p2p channels per peer
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) jpbo-026-41:380145:380620 [0] NCCL INFO TUNER/Plugin: Could not find: libnccl-tuner.so. Using internal tuner plugin.
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) jpbo-026-41:380145:380620 [0] NCCL INFO ncclCommInitRankConfig comm 0xaaab14413a40 rank 5 nranks 49 cudaDev 0 nvmlDev 0 busId 901000 commId 0xa8aa92223a1db3f3 - Init COMPLETE
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) jpbo-026-41:380145:380620 [0] NCCL INFO Init timings - ncclCommInitRankConfig: rank 5 nranks 49 total 3.38 (kernels 0.32, alloc 2.10, bootstrap 0.28, allgathers 0.01, topo 0.03, graphs 0.01, connections 0.63, rest 0.01)
(AsyncVLLMInferenceEngine pid=301251, ip=10.128.25.163) 33f250
(AsyncVLLMInferenceEngine pid=301252, ip=10.128.25.163) 095833f6f0
(AsyncVLLMInferenceEngine pid=349371, ip=10.128.25.161) 0485760 ipcDesc 0x40097033fc50
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986) INFO 06-12 01:05:24 [kernel_warmup.py:44] Skipping FlashInfer autotune because it is disabled. [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=315936, ip=10.128.25.23) size 10485760 ipcDesc 0x40097833bd20
(AsyncVLLMInferenceEngine pid=316064, ip=10.128.25.23) 3[1] via P2P/IPC
(AsyncVLLMInferenceEngine pid=316063, ip=10.128.25.23) : 3[1] -> 2[0] via P2P/IPC
(AsyncVLLMInferenceEngine pid=300698, ip=10.128.25.162) d20
(AsyncVLLMInferenceEngine pid=300699, ip=10.128.25.162) 433fbc0
(AsyncVLLMInferenceEngine pid=316510, ip=10.128.25.28) ed shareable buffer 0x40179c600000 size 10485760 ipcDesc 0x40095c33fd50
(AsyncVLLMInferenceEngine pid=316640, ip=10.128.25.28) 5033d590
(AsyncVLLMInferenceEngine pid=316639, ip=10.128.25.28) 96833fda0
(AsyncVLLMInferenceEngine pid=304566, ip=10.128.25.165) 33fd70
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) 833fc30
(AsyncVLLMInferenceEngine pid=478789, ip=10.128.25.176) c 0x4009781d4530
(AsyncVLLMInferenceEngine pid=478790, ip=10.128.25.176) ize 2097152 ipcDesc 0x400970015eb0
(AsyncVLLMInferenceEngine pid=326155, ip=10.128.25.27) c60
(AsyncVLLMInferenceEngine pid=326287, ip=10.128.25.27) 433eca0
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) vice 0 size 2097152 ptr 0x4017be200000
(AsyncVLLMInferenceEngine pid=249097, ip=10.128.25.24) shareable buffer 0x40179c600000 size 10485760 ipcDesc 0x40096833fcd0
(AsyncVLLMInferenceEngine pid=249225, ip=10.128.25.24) 3fc90
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) 95433fe50
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO AllReduce: opCount ff sendbuff 0x400e9fa88c00 recvbuff 0x400e9fa88c00 count 1 datatype 7 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x401820000000 recvbuff 0x401660000000 count 155582464 datatype 9 op 0 root 0 comm 0x400dfaa9fd00 [nranks=4] stream 0x400dfa7c8310
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO Channel 00/08 : 0 16 15 14 1 2 3 4 13 8 7 6 5 9 10 11 12 20 19 18 17 21 22 23 24 40 39 38 25 26 27 28 37 32 31 30 ...
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO Channel 01/08 : 0 1 14 15 16 13 4 3 2 5 6 7 8 12 11 10 9 17 18 19 20 24 23 22 21 25 38 39 40 37 28 27 26 29 30 31 ...
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO Channel 02/08 : 0 14 1 16 15 4 2 13 3 6 5 8 7 11 9 12 10 18 17 20 19 23 21 24 22 38 25 40 39 28 26 37 27 30 29 32 ...
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO Channel 03/08 : 0 15 1 16 14 3 2 13 4 7 5 8 6 10 9 12 11 19 17 20 18 22 21 24 23 39 25 40 38 27 26 37 28 31 29 32 ...
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO Channel 04/08 : 0 16 15 14 1 2 3 4 13 8 7 6 5 9 10 11 12 20 19 18 17 21 22 23 24 40 39 38 25 26 27 28 37 32 31 30 ...
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO Channel 05/08 : 0 1 14 15 16 13 4 3 2 5 6 7 8 12 11 10 9 17 18 19 20 24 23 22 21 25 38 39 40 37 28 27 26 29 30 31 ...
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO Channel 06/08 : 0 14 1 16 15 4 2 13 3 6 5 8 7 11 9 12 10 18 17 20 19 23 21 24 22 38 25 40 39 28 26 37 27 30 29 32 ...
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO Channel 07/08 : 0 15 1 16 14 3 2 13 4 7 5 8 6 10 9 12 11 19 17 20 18 22 21 24 23 39 25 40 38 27 26 37 28 31 29 32 ...
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO Check P2P Type isAllDirectP2p 0 directMode 0
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO CC Off, workFifoBytes 1048576
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount 0 sendbuff 0x401660000000 recvbuff 0x401660000000 count 622329856 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO AllReduce: opCount 100 sendbuff 0x400e9fa88e00 recvbuff 0x400e9fa88e00 count 1 datatype 7 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x401635c00000 recvbuff 0x401913c00000 count 4194304 datatype 9 op 0 root 0 comm 0x400dfaa9fd00 [nranks=4] stream 0x400dfa7c8310
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount 1 sendbuff 0x401913c00000 recvbuff 0x401913c00000 count 16777216 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO AllReduce: opCount 101 sendbuff 0x400e9
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986) INFO 06-12 01:05:24 [core.py:278] init engine (profile, create kv cache, warmup model) took 4.08 seconds [repeated 3x across cluster]
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO AllReduce: opC
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) INFO Broadcast: opCount fa sendbuff 0x400e99e2b600 recvbuff 0x400e99e2b600 count 128 datatype 9 op 0 root 0 comm 0x400e112e5db0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400e99e2b800 count 32 datatype 9 op 0 root 0 comm 0x400e116cc830 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400e99e2b600 count 32 datatype 9 op 0 root 0 comm 0x400e116cc830 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x4010f8a00000 count 12582912 datatype 9 op 0 root 0 comm 0x400e116cc830 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x4010fa200000 count 12582912 datatype 9 op 0 root 0 comm 0x400e116cc830 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x4010fba00000 count 12582912 datatype 9 op 0 root 0 comm 0x400e116cc830 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400e99e2ba00 count 1024 datatype 9 op 0 root 0 comm 0x400e116cc830 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400e99e2c200 count 1024 datatype 9 op 0 root 0 comm 0x400e116cc830 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x400e99e2f600 count 1024 datatype 9 op 0 root 0 comm 0x400e116cc830 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x40116a400000 count 155582464 datatype 9 op 0 root 0 comm 0x400e116cc830 [nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x4012f3e00000 recvbuff 0x401760000000 count 12582912 datatype 9 op 0 root 0 comm 0x400e116cc830 [nranks=4] strea
(FSDPPolicyWorkerBase pid=364947) tream (nil)
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO AllGather: op
(FSDPPolicyWorkerBase pid=364944) ream (nil)
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO AllGather: opC
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) fa88c00 recvbuff 0x400e9fa88c00 count 1 datatype 7 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount a sendbuff 0x400e9fa88e00 recvbuff 0x400e9fa88e00 count 4096 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount b sendbuff 0x400e9fa8b000 recvbuff 0x400e9fa8b000 count 4096 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount c sendbuff 0x401913c00000 recvbuff 0x401913c00000 count 16777216 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount d sendbuff 0x401389580000 recvbuff 0x401389580000 count 4194304 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount e sendbuff 0x401913c00000 recvbuff 0x401913c00000 count 4194304 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount f sendbuff 0x401660000000 recvbuff 0x401660000000 count 16777216 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO Al
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) nranks=4] stream (nil)
(FSDPPolicyWorkerBase pid=364946) ount 108 sendbuff 0x400edfa88c00 recvbuff 0x400edfa88c00 count 1 datatype 7 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) 7 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO AllGather: opCount 0 sendb
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) lGather: opCount 0 sendbuff 0x400e9fa5b600 recvbuff 0x400e9fa88e00 count 32 datatype 9 op 0 root 0 comm 0x400dfaa9fd00 [nranks=4] stream 0x400dfa7c8310
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) m 0x400e113f9600
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e89000 recvbuff 0x400e99e89000 count 1 datatype 7 op 0 root
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) 0x400e093f6c80
(FSDPPolicyWorkerBase pid=364947) Count 0 sendbuff 0x4012d3a00000 recvbuff 0x4017aa400000 count 1048576 datatype 9 op 0 root 0 comm 0x400e416caff0 [nranks=4] stream 0x400e413f9160
(FSDPPolicyWorkerBase pid=364947) jpbo-026
(FSDPPolicyWorkerBase pid=364944) ount 0 sendbuff 0x4012d3a00000 recvbuff 0x4017aa400000 count 1048576 datatype 9 op 0 root 0 comm 0x400e416cc220 [nranks=4] stream 0x400e413f8020
(FSDPPolicyWorkerBase pid=364944) jpbo-026-
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442312 [0] NCCL INFO AllReduce: opCount 18f sendbuff 0x400eb9e88e00 recvbuff 0x400eb9e88e00 count 1 datatype 7 op
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) jpbo-029-46:443488:443488 [0] NCCL INFO Broadcast: opCount 2a sendbuff 0x401720000000 recvbuff 0x401720000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaab28ec7140 [nran
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) jpbo-029-46:443505:443505 [0] NCCL INFO Broadcast: opCount 1c sendbuff 0x401740000000 recvbuff 0x401740000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaab032e5280 [nranks=49] s
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986) WARNING 06-12 01:05:24 [serial_utils.py:57] Allowing insecure serialization using pickle due to VLLM_ALLOW_INSECURE_SERIALIZATION=1 [repeated 3x across cluster]
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x401860000000 recvbuff 0x4016a0000000 count 12582912 datatype 9 o
(FSDPPolicyWorkerBase pid=364945) uff 0x400eb9e2ea00 recvbuff 0x400eb9e88e00 count 1024 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream 0x400e613efdc0
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) c8310
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount 2c sendbuff 0x400e9fa8b000 recvbuff 0x400e9fa8b000 count 4096 datatype 9 op 0
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) 0 comm 0x400e112e5db0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x400e99e32c00 recvbuff 0x400e99
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO AllReduce: opCount 13a sendbuff 0x400e9fa8
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986) INFO 06-12 01:05:24 [vllm.py:690] Asynchronous scheduling is enabled. [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986) WARNING 06-12 01:05:24 [vllm.py:735] Inductor compilation was disabled by user settings, optimizations settings that are only active during inductor compilation will be ignored. [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) (EngineCore_DP0 pid=304986) INFO 06-12 01:05:24 [vllm.py:846] Cudagraph is disabled under eager mode [repeated 3x across cluster]
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442312 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x4010f4a0
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e88c00 recvbuff 0x400e99e88c00 count 1 datatype 7 op 0 root 0 comm 0x400e412e5990 [
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e88c00 recvbuff 0x400e99e88c00 count 1 datatype 7 op 0 root 0 comm 0x400e412e4700 [n
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) e88c00 count 32 datatype 9 op 0 root 0 comm 0x400e116cc830 [nranks=4] stream 0x400e113f9600
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO AllReduce: opCoun
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) WARNING 06-12 01:05:25 [model.py:1350] Default vLLM sampling parameters have been overridden by the model's `generation_config.json`: `{'temperature': 0.6, 'top_k': 20, 'top_p': 0.95}`. If this is not intended, please relaunch vLLM instance with `--generation-config vllm`. [repeated 3x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount 3a sendbuff 0x401913c00000 recvbuff 0x401913c00000 count 4194304 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil) [repeated 1717x across cluster]
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO Send: opCount 0 sendbuff (nil) recvbuff 0x4016d7a40000 count 155582464 datatype 9 op 0 root 3 comm 0x400e06a9e080 [nranks=4] stream (nil) [repeated 15x across cluster]
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442310 [0] NCCL INFO Broadcast: opCount fa sendbuff 0x4010e0000000 recvbuff 0x4010e0000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e092e33d0 [nranks=8] stream (nil) [repeated 4x across cluster]
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442310 [0] NCCL INFO Broadcast: opCount fb sendbuff 0x4010e6000000 recvbuff 0x4010e6000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e092e33d0 [nranks=8] stream (nil) [repeated 2x across cluster]
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442310 [0] NCCL INFO Broadcast: opCount fc sendbuff 0x4010e0000000 recvbuff 0x4010e0000000 count 50331648 datatype 9 op 0 root 0 comm 0x400e092e33d0 [nranks=8] stream (nil) [repeated 3x across cluster]
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO Broadcast: opCount fd sendbuff 0x401100000000 recvbuff 0x401100000000 count 622329856 datatype 9 op 0 root 0 comm 0x400e412e4700 [nranks=8] stream (nil) [repeated 20x across cluster]
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e88e00 recvbuff 0x400e99e88e00 count 1 datatype 7 op 0 root 0 comm 0x400e112e5db0 [nranks=8] stream (nil) [repeated 240x across cluster]
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442310 [0] NCCL INFO AllReduce: opCount
(FSDPPolicyWorkerBase pid=364946) p 0 root 0 comm 0x400e06a9e080 [nranks=4] stream 0x400e067c71c0
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO AllReduce: opCount 148 sendbuf
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) 8c00 recvbuff 0x400e9fa88c00 count 1 datatype 7 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO AllGather
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) 0000 recvbuff 0x401718c00000 count 1048576 datatype 9 op 0 root 0 comm 0x400e256ca1f0 [nranks=4] stream 0x400e253f6520
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:44
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x4012e9400000 recvbuff 0x4017aa400000 count 4194304 datatype
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) jpbo-029-37:304985:304985 [0] NCCL INFO Broadcast: opCount 55 sendbuff 0x401760000000 recvbuff 0x401760000000 count 50331648 datatype 9 op 0 root
(AsyncVLLMInferenceEngine pid=304568, ip=10.128.25.165) jpbo-029-37:304987:304987 [0] NCCL INFO Broadcast: opCount 37 sendbuff 0x401720000000 recvbuff 0x401720000000 count 50331648 datatype 9 op 0 root 0 comm 0
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) : opCount 0 sendbuff 0x40184e400000 recvbuff 0x401660000000 count 12582912 datatype 9 op 0 root 0 comm 0x400dfaa9fd00 [nranks=4] stream 0x400dfa7c8310
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) t fe sendbuff 0x400e99e88c00 recvbuff 0x400e99e88c00 count 1 datatype 7 op 0 root 0 comm 0x400e112e5db0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:44
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442312 [0] NCCL INFO AllReduce: opCount 18f sendbuff 0x400eb9e88e00 recvbuff 0x400eb9e88e00 count 1 datatype 7 op 0 root 0 comm
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) fe sendbuff 0x400e99e88c00 recvbuff 0x400e99e88c00 count 1 datatype 7 op 0 root 0 comm 0x400e092e33d0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442
(FSDPPolicyWorkerBase pid=364947) 9 op 0 root 0 comm 0x400e416caff0 [nranks=4] stream 0x400e413f9160
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e88e00
(FSDPPolicyWorkerBase pid=364946) f 0x400edfa89000 recvbuff 0x400edfa89000 count 1 datatype 7 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e88e00 r
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount 65 sendbuff 0x401389580000 recvbuff 0x401389580000 count 4194304 dat
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:3649
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) atype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO AllReduce: opCount 173 sendbuff 0x400e9
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x400faa000000 recvbuff 0x401760000000 count 4194304 datatype 9 op 0 root 0 comm 0x400e116cc830 [nranks=4
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO AllGather: o
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x400edfa67a00 recvbuff 0x400edfa88e00 count 32 datatype 9 op 0 root 0
(FSDPPolicyWorkerBase pid=364944) ecvbuff 0x400e99e88e00 count 1 datatype 7 op 0 root 0 comm 0x400e412e4700 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442312 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x400eb9e3ae00 recvbu
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) jpbo-029-46:443488:443488 [0] NCCL INFO Broadcast: opCount 80 sendbuff 0x401720000000 recvbuff 0x401720000000 count 503
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) jpbo-029-46:443505:443505 [0] NCCL INFO Broadcast: opCount 52 sendbuff 0x401740000000 recvbuff 0x401740000000 count 50331648 da
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) ] stream 0x400e113f9600
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e88c00 recvbuff 0x400e99e88c00 count 1 datatype 7 o
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) stream 0x400e093f6c80
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442310 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e88c00 recvbuff 0x400e99e88c00 count 1 datatype 7 op
(FSDPPolicyWorkerBase pid=364947) pCount 0 sendbuff 0x400e99e3ae00 recvbuff 0x400e99e8b000 count 1024 datatype 9 op 0 root 0 comm 0x400e416caff0 [nranks=4] stream 0x400e413f9160
(FSDPPolicyWorkerBase pid=364947) jpbo-02
(FSDPPolicyWorkerBase pid=364946) comm 0x400e06a9e080 [nranks=4] stream 0x400e067c71c0
(FSDPPolicyWorkerBase pid=364944) jpbo-026
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) INFO AllGather: opCount 0 sendbuff 0x40186e800000 recvbuff 0x401660000000 count 12582912 datatype 9 op 0 root 0 comm 0x400dfaa9fd00 [nranks=4] stream 0x400dfa7c8310
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x401870800000 recvbuff 0x401913c00000 count 4194304 datatype 9 op 0 root 0 comm 0x400dfaa9fd00 [nranks=4] str
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) ff 0x400eb9e8b000 count 1024 datatype 9 op 0 root 0 comm 0x400e256ca1f0 [nranks=4] stream 0x400e253f6520
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442312
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x400eb9e3e000 recvbuf
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e88e00 recvbuff 0x400e99e88e00 count 1 datatype 7 op 0 root 0 comm 0x400e412e59
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:36
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) eam 0x400dfa7c8310
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) p 0 root 0 comm 0x400e112e5db0 [nranks=8] stream (nil)
(AsyncVLLMInferenceEngine pid=249097, ip=10.128.25.24) 31648 datatype 9 op 0 root 0 comm 0xaaab02e90db0 [nranks=49] stream (nil)
(AsyncVLLMInferenceEngine pid=249097, ip=10.128.25.24) jpbo-026-40:249632:249632 [0] NCCL INFO Broadcast: opCount aa sendbuff 0x4003bdd82400 recvbuff 0x4003bdd82400 count 128 datatype 9 op 0 root 0 comm 0xaaab02e90db0 [nranks=49] stream (nil)
(AsyncVLLMInferenceEngine pid=249097, ip=10.128.25.24) jpbo-026-40:249632:249632 [0] NCCL INFO Broadcast: opCount ab sendbuff 0x4003bdd82400 r
(AsyncVLLMInferenceEngine pid=249227, ip=10.128.25.24) tatype 9 op 0 root 0 comm 0xaaab2a5a1f40 [nranks=49] stream (nil)
(AsyncVLLMInferenceEngine pid=249227, ip=10.128.25.24) jpbo-026-40:249633:249633 [0] NCCL INFO Broadcast: opCount 6e sendbuff 0x4003bdd82400 recvbuff
(FSDPPolicyWorkerBase pid=364945) f 0x400eb9e88c00 count 32 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream 0x400e613efdc0
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount ab sendbuff 0x400e9fa88c00 recvbuff 0x400e9fa88c00 count 128 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount ac sendbuff 0x401660000000 recvbuff 0x401660000000 count 50331648 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442310 [0] NCCL INFO AllReduce: opCo
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x401325c00000 recvbuff 0x401760000000 count 12582912 data
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x401328c00000 recvbuff 0x401760000000 count 12582912 datat
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount ad sendbuff 0x401666000000 recvbuff 0x401666000000 count 50331648 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount ae sendbuff 0x401660000000 recvbuff 0x401660000000 count 50331648 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount af sendbuff 0x400e9fa88e00 recvbuff 0x400e9fa88e00 count 4096 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount ba sendbuff 0x400e9fa88e00 recvbuff 0x400e9fa88e00 count 4096 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) ount fe sendbuff 0x400e99e88e00 recvbuff 0x400e99e88e00 count 1 datatype 7 op 0 root 0 comm 0x400e112e5db0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:4423
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) unt fe sendbuff 0x400e99e88e00 recvbuff 0x400e99e88e00 count 1 datatype 7 op 0 root 0 comm 0x400e092e33d0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:44231
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount bb sendbuff 0x400e9fa8b000 recvbuff 0x400e9fa8b000 count 4096 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount bc sendbuff 0x401913c00000 recvbuff 0x401913c00000 count 16777216 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount bd sendbuff 0x401389580000 recvbuff 0x401389580000 count 4194304 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount be sendbuff 0x401913c00000 recvbuff 0x401913c00000 count 4194304 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount bf sendbuff 0x401660000000 recvbuff 0x401660000000 count 16777216 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x40188e200000 recvbuff 0x401913c00000 count 1048576 datatype 9 op 0 root 0 comm 0x400dfaa9fd00 [n
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO AllReduce: opCount 1c8 sendbuff 0x400edfa88e00 r
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442312 [0] NCCL IN
(FSDPPolicyWorkerBase pid=364947) type 9 op 0 root 0 comm 0x400e416caff0 [nranks=4] stream 0x400e413f9160
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e88c
(FSDPPolicyWorkerBase pid=364944) ype 9 op 0 root 0 comm 0x400e416cc220 [nranks=4] stream 0x400e413f8020
(AsyncVLLMInferenceEngine pid=249097, ip=10.128.25.24) jpbo-026-40:249632:249632 [0] NCCL INFO Broadcast: opCount ca sendbuff 0x4016d9800000 recvbuff 0x4016d9800000 count 16777216 datatype 9 op 0 root 0 comm 0xaaab02e90db0 [nranks=49] stream (nil)
(AsyncVLLMInferenceEngine pid=249097, ip=10.128.25.24) jpbo-026-40:249632:249632 [0] NCCL INFO Broadcast: opCount cb sendbuff 0x4003bdd82400 recvbuff 0x4003bdd82400 count 128 datatype 9 op 0 root 0 comm 0xaaab02e90db0 [nranks=49] stream (nil)
(AsyncVLLMInferenceEngine pid=249097, ip=10.128.25.24) jpbo-026-40:249632:249632 [0] NCCL INFO Broadcast: opCount cc sendbuff 0x4003bdd82400 recvbuff 0x4003bdd82400 count 128 datatype 9 op 0 root 0 comm 0xaaab02e90db0 [nranks=49] stream (nil)
(AsyncVLLMInferenceEngine pid=249097, ip=10.128.25.24) jpbo-026-40:249632:249632 [0] NCCL INFO Broadcast: opCount cd sendbuff 0x401740000000 recvbuff 0x401740000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaab02e90db0 [nranks=49] stream (nil)
(AsyncVLLMInferenceEngine pid=249097, ip=10.128.25.24) jpbo-026-40:249632:249632 [0] NCCL INFO Broadcast: opCount ce sendbuff 0x401740000000 recvbuff 0x401740000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaab02e90db0 [nranks=49] stream (nil)
(AsyncVLLMInferenceEngine pid=249097, ip=10.128.25.24) jpbo-026-40:249632:249632 [0] NCCL INFO Broadcast: opCount cf sendbuff 0x401740000000 recvbuff 0x401740000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaab02e90db0 [nranks=49] stream (nil)
(AsyncVLLMInferenceEngine pid=249097, ip=10.128.25.24) jpbo-026-40:249632:249632 [0] NCCL INFO Broadcast: opCo
(AsyncVLLMInferenceEngine pid=249227, ip=10.128.25.24) 0x4003bdd82400 count 128 datatype 9 op 0 root 0 comm 0xaaab2a5a1f40 [nranks=49] stream (nil)
(AsyncVLLMInferenceEngine pid=249227, ip=10.128.25.24) jpbo-026-40:249633:249633 [0] NCCL INFO Broadcast: opCount 8a s
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) FO AllReduce: opCount 18f sendbuff 0x400eb9e88c00 recvbuff 0x400eb9e88c00 count 1 datatype 7 op 0 root 0 comm 0x400e252e2e80 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442310 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x401336400000 recvbuff 0x4017aa400000 count 4194304 datatype 9 op 0 root 0 comm 0x400e096cb190 [nranks=4] s
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO AllGather: opC
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount da sendbuff 0x401660000000 recvbuff 0x401660000000 count 50331648 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount db sendbuff 0x400e9fa88e00 recvbuff 0x400e9fa88e00 count 4096 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount dc sendbuff 0x400e9fa8b000 recvbuff 0x400e9fa8b000 count 4096 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount dd sendbuff 0x401913c00000 recvbuff 0x401913c00000 count 16777216 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount de sendbuff 0x401389580000 recvbuff 0x401389580000 count 4194304 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount df sendbuff 0x401913c00000 recvbuff 0x401913c00000 count 4194304 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) e5 sendbuff 0x400e9fa88e00 recvbuff 0x400e9fa88e00 count 1 datatype 7 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount ea sendbuff 0x401913c00000 recvbuff 0x401913c00000 count 4194304 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount eb sendbuff 0x401660000000 recvbuff 0x401660000000 count 16777216 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount ec sendbuff 0x400e9fa88e00 recvbuff 0x400e9fa88e00 count 128 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount ed sendbuff 0x400e9fa88c00 recvbuff 0x400e9fa88c00 count 128 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount ee sendbuff 0x401660000000 recvbuff 0x401660000000 count 50331648 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount ef sendbuff 0x401666000000 recvbuff 0x401666000000 count 50331648 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:44
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) tream 0x400e093f6c80
(FSDPPolicyWorkerBase pid=364947) jpbo-026
(FSDPPolicyWorkerBase pid=364944) ount 0 sendbuff 0x40133e400000 recvbuff 0x401766000000 count 12582912 datatype 9 op 0 root 0 comm 0x400e416cc220 [nranks=4] stream 0x400e413f8020
(FSDPPolicyWorkerBase pid=364944) jpbo-026-
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) ] stream (nil)
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442312 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x401339c00000 recvbuff 0x401760000000 count 1258
(AsyncVLLMInferenceEngine pid=349371, ip=10.128.25.161) unt d6 sendbuff 0x4003ddd82400 recvbuff 0x4003ddd82400 count 128 datatype 9 op 0 root 0 comm 0xaaab1bf56550 [nranks=49] stream (nil)
(AsyncVLLMInferenceEngine pid=349371, ip=10.128.25.161) jpbo-029-33:349999:349999 [0] NCCL INFO Broadcast: opCount fe sendbuff 0x4016f9800000 recvbuff 0x4016f9800000 count 16777216 datatype 9 op 0 root 0 comm 0xaaab1bf56550 [nranks=49] stream (nil)
(AsyncVLLMInferenceEngine pid=349371, ip=10.128.25.161) jpbo-029-33:349999:349999 [0] NCCL INFO Broadcast: opCount ff sendbuff 0x401759200000 recvbuff 0x401759200000 count 4194304 datatype 9 op 0 root 0 comm 0xaaab1bf56550 [nranks=49] stream (nil)
(AsyncVLLMInferenceEngine pid=349499, ip=10.128.25.161) endbuff 0x4003bdd82400 recvbuff 0x4003bdd82400 count 128 datatype 9 op 0 root 0 comm 0xaaab1d4cfe60 [nranks=49] stream (nil)
(AsyncVLLMInferenceEngine pid=349499, ip=10.128.25.161) jpbo-029-33:350003:350003 [0] NCCL I
(FSDPPolicyWorkerBase pid=364945) INFO AllReduce: opCount 18f sendbuff 0x400eb9e88c00 recvbuff 0x400eb9e88c00 count 1 datatype 7 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO AllReduce: opCount 18f sendbuff 0x400eb9e88e00 recvbuff 0x400eb9e88e00 count 1 datatype 7 op 0 root 0 comm 0x400e612dc480 [nrank
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO AllReduce: opCount 208 sendbuff 0x400edfa88e00 recvbuff 0x400e
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e89000 recvbuff 0x400e99e89000 count 1 datatype 7 op 0 root 0 comm 0x400e412e4700 [nr
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount 110 sendbuff 0x401666000000 recvb
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) 2912 datatype 9 op 0 root 0 comm 0x400e256ca1f0 [nranks=4] stream 0x400e253f6520
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442312 [0] NCCL INFO AllReduce: op
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) uff 0x401666000000 count 50331648 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0]
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO AllGat
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) Count 18f sendbuff 0x400eb9e89000 recvbuff 0x400eb9e89000 count 1 datatype 7 op 0 root 0 comm 0x400e252e2e80 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442312 [0] NCCL INFO AllReduce: opCount 18f sendbuff 0x400eb9e88c00 recvbuff 0x400eb9e88c00 count 1 datatype 7 op 0 root 0 comm 0x400e252e2e80 [nranks=8] stream (
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO AllReduce
(AsyncVLLMInferenceEngine pid=304439, ip=10.128.25.165) jpbo-029-37:304985:304985 [0] NCCL INFO Broadcast: opCount 12b sendbuff 0x401759200000 recvbuff 0x401759200000 count 4194304 datatype 9 op 0 root 0 c
(AsyncVLLMInferenceEngine pid=478789, ip=10.128.25.176) NFO Broadcast: opCount a5 sendbuff 0x4016f9800000 recvbuff 0x4016f9800000 count 16777216 datatype 9 op 0 root 0 comm 0xaaab063e0f80 [nranks=49] stream (nil)
(AsyncVLLMInferenceEngine pid=478789, ip=10.128.25.176) jpbo-029
(AsyncVLLMInferenceEngine pid=478791, ip=10.128.25.176) jpbo-029
(AsyncVLLMInferenceEngine pid=249227, ip=10.128.25.24) jpbo-026
(AsyncVLLMInferenceEngine pid=249225, ip=10.128.25.24) jpbo-026
(AsyncVLLMInferenceEngine pid=379729, ip=10.128.25.25) jpbo-026
(AsyncVLLMInferenceEngine pid=379730, ip=10.128.25.25) jpbo-026
(AsyncVLLMInferenceEngine pid=305554, ip=10.128.25.164) jpbo-029
(AsyncVLLMInferenceEngine pid=305556, ip=10.128.25.164) jpbo-029
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) jpbo-029
(AsyncVLLMInferenceEngine pid=443231, ip=10.128.25.174) jpbo-029
(AsyncVLLMInferenceEngine pid=301250, ip=10.128.25.163) jpbo-029
(AsyncVLLMInferenceEngine pid=301251, ip=10.128.25.163) jpbo-029
(AsyncVLLMInferenceEngine pid=349499, ip=10.128.25.161) jpbo-029
(AsyncVLLMInferenceEngine pid=349500, ip=10.128.25.161) jpbo-029
(AsyncVLLMInferenceEngine pid=316064, ip=10.128.25.23) jpbo-026
(AsyncVLLMInferenceEngine pid=316063, ip=10.128.25.23) jpbo-026
(AsyncVLLMInferenceEngine pid=300698, ip=10.128.25.162) jpbo-029
(AsyncVLLMInferenceEngine pid=300697, ip=10.128.25.162) jpbo-029
(AsyncVLLMInferenceEngine pid=316638, ip=10.128.25.28) jpbo-026
(AsyncVLLMInferenceEngine pid=316640, ip=10.128.25.28) jpbo-026
(AsyncVLLMInferenceEngine pid=304568, ip=10.128.25.165) jpbo-029
(AsyncVLLMInferenceEngine pid=304566, ip=10.128.25.165) jpbo-029
(AsyncVLLMInferenceEngine pid=326288, ip=10.128.25.27) jpbo-026
(AsyncVLLMInferenceEngine pid=326287, ip=10.128.25.27) jpbo-026
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) jpbo-026
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) Count fe sendbuff 0x400e99e88c00 recvbuff 0x400e99e88c00 count 1 datatype 7 op 0 root 0 comm 0x400e112e5db0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:4
(FSDPPolicyWorkerBase pid=364946) her: opCount 0 sendbuff 0x400edfa7b200 recvbuff 0x400edfa8b000 count 1024 datatype 9 op 0 root 0 comm 0x400e06a9e080 [nranks=4] stream 0x400e067c71c0
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x400edfa7d200 recvbuff 0x400edfa88e00 count 1024 datatype 9 op 0 root 0 comm 0x400e06a9e080 [nranks=4] st
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) nil)
(FSDPPolicyWorkerBase pid=364945) : opCount 18f sendbuff 0x400eb9e88c00 recvbuff 0x400eb9e88c00 count 1 datatype 7 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO AllReduce: opCount 18f sendbuff 0x400eb9e88e00 recvbuff 0x400eb9e88e00 count 1 datatype 7 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (n
(FSDPPolicyWorkerBase pid=364946) ream 0x400e067c71c0
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO AllReduce: opCount 248 sendbuff 0x400edfa88e00 recvbuff 0x400edfa88e00
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:44260
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x401391400000 recvbuff 0x401760000000 count 12582912 datatype 9 op 0 root 0 comm 0x400e116cc830 [nranks
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442310 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x401374400000 recvbuff 0x401760000000 count 12582912 datatype 9 op 0 root 0 comm 0x400e096cb190 [nranks=
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO AllGath
(AsyncVLLMInferenceEngine pid=478659, ip=10.128.25.176) omm 0xaaab25495c20 [nranks=49] stream (nil)
(AsyncVLLMInferenceEngine pid=478659, ip=10.128.25.176) jpbo-029-48:479197:479197 [0] NCCL INFO Broadcast: opCount 156 sendbuff 0x4016d
(AsyncVLLMInferenceEngine pid=478789, ip=10.128.25.176) jpbo-029-48:479189:479189 [0] NCCL INFO Broadcast: opCount da sendbuff 0x4016f9800000 recvbuff 0x4016f9800000 count 16777216 datatype 9 op 0 root 0 comm 0xaaab063e0f80 [nran
(FSDPPolicyWorkerBase pid=364945) il)
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x400eb9e53e00 recvbuff 0x400eb9e8b000 count 1024 dataty
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e88c00 recvbuff 0x400e99e88c00 count 1 datatype 7
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO AllGather: opCount
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) t 18f sendbuff 0x400eb9e88e00 recvbuff 0x400eb9e88e00 count 1 datatype 7 op 0 root 0 comm 0x400e252e2e80 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo
(FSDPPolicyWorkerBase pid=364947) j
(FSDPPolicyWorkerBase pid=364944) er: opCount 0 sendbuff 0x400e99e53200 recvbuff 0x400e99e88e00 count 32 datatype 9 op 0 root 0 comm 0x400e416cc220 [nranks=4] stream 0x400e413f8020
(FSDPPolicyWorkerBase pid=364945) pe 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream 0x400e613efdc0
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO AllReduce: opCount 265 sendbuff 0x400e9fa88c00 recv
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) buff 0x400e9fa88c00 count 1 datatype 7 op 0 root 0 comm 0x400dfa6b40c0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NC
(FSDPPolicyWorkerBase pid=364946) 0 sendbuff 0x401900000000 recvbuff 0x4016a0000000 count 12582912 datatype 9 op 0 root 0 comm 0x400e06a9e080 [nranks=4] stream 0x400e067c71c0
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442312 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x401379800000 recvbuff 0x4017aa400000 count 1048576 datatype 9 op
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) jpbo-029-46:443494:443494 [0] NCCL INFO cudaDriverVersion 13020 [repeated 47x across cluster]
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) jpbo-029-46:443494:443494 [0] NCCL INFO NCCL version 2.27.7+cuda13.0 [repeated 47x across cluster]
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) jpbo-029-46:443494:444068 [0] NCCL INFO NET/Plugin: Could not find: libnccl-net.so.  [repeated 47x across cluster]
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) jpbo-029-46:443494:444068 [0] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_1:1/IB [2]mlx5_2:1/IB [3]mlx5_3:1/IB [RO]; OOB ib0:10.128.25.174<0> [repeated 47x across cluster]
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) jpbo-029-46:443494:444068 [0] NCCL INFO Initialized NET plugin IB [repeated 47x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO Assigned NET plugin IB to comm [repeated 48x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO Using network IB [repeated 48x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO DMA-BUF is available on GPU device 0 [repeated 48x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO ncclCommInitRankConfig comm 0x400ef44ecc80 rank 0 nranks 49 cudaDev 0 nvmlDev 0 busId 901000 commId 0xa8aa92223a1db3f3 - Init START [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) jpbo-029-46:443494:444068 [0] NCCL INFO RAS client listening socket at 127.0.0.1<28028> [repeated 47x across cluster]
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) jpbo-029-46:443494:444068 [0] NCCL INFO NCCL_NET_GDR_LEVEL set by environment to LOC [repeated 47x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO Setting affinity for GPU 0 to 0-71 [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) jpbo-029-46:443494:444068 [0] NCCL INFO NVLS multicast support is not available on dev 0 (NVLS_NCHANNELS 0) [repeated 47x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO comm 0x400ef44ecc80 rank 0 nRanks 49 nNodes 13 localRanks 1 localRank 0 MNNVL 0 [repeated 48x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO Trees [0] 26/-1/-1->0->-1 [1] 27/-1/-1->0->-1 [2] 28/-1/-1->0->-1 [3] 37/-1/-1->0->-1 [4] 41/-1/-1->0->29 [5] 42/-1/-1->0->30 [6] 43/-1/-1->0->31 [7] 44/-1/-1->0->32 [repeated 48x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO P2P Chunksize set to 131072 [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) jpbo-029-46:443494:444068 [0] NCCL INFO PROFILER/Plugin: Could not find: libnccl-profiler.so.  [repeated 47x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442612 [0] NCCL INFO [Proxy Service] Device 0 CPU core 51 [repeated 48x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442613 [0] NCCL INFO [Proxy Service UDS] Device 0 CPU core 52 [repeated 48x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442614 [0] NCCL INFO [Proxy Progress] Device 0 CPU core 54 [repeated 48x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO Channel 07/0 : 0[0] -> 44[3] [send] via NET/IB/0 [repeated 282x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO Channel 00/0 : 26[0] -> 0[0] [receive] via NET/IB/0 [repeated 279x across cluster]
(AsyncVLLMInferenceEngine pid=249225, ip=10.128.25.24) jpbo-026-40:249625:250043 [0] NCCL INFO Channel 06/0 : 22[1] -> 21[0] via P2P/IPC [repeated 654x across cluster]
(AsyncVLLMInferenceEngine pid=249225, ip=10.128.25.24) jpbo-026-40:249625:250071 [0] NCCL INFO Allocated shareable buffer 0x40177e600000 size 2097152 ipcDesc 0x40094433fc90 [repeated 1312x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) jpbo-026-40:249637:250044 [0] NCCL INFO Imported shareable buffer device 0 size 10485760 ptr 0x4016dd800000 [repeated 1331x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO Connected all rings, use ring PXN 0 GDR 0 [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=326288, ip=10.128.25.27) jpbo-026-43:326764:327196 [0] NCCL INFO Allocated shareable buffer 0x40177e000000 size 2097152
(FSDPPolicyWorkerBase pid=364944) jp [repeated 2x across cluster]
(AsyncVLLMInferenceEngine pid=379601, ip=10.128.25.25) jpbo-
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO Connected all trees [repeated 48x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO threadThresholds 8/8/64 | 392/8/64 | 512 | 512 [repeated 48x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO 8 coll channels, 8 collnet channels, 0 nvls channels, 8 p2p channels, 1 p2p channels per peer [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) jpbo-026-40:249637:250044 [0] NCCL INFO TUNER/Plugin: Could not find: libnccl-tuner.so. Using internal tuner plugin. [repeated 47x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO ncclCommInitRankConfig comm 0x400ef44ecc80 rank 0 nranks 49 cudaDev 0 nvmlDev 0 busId 901000 commId 0xa8aa92223a1db3f3 - Init COMPLETE [repeated 48x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442611 [0] NCCL INFO Init timings - ncclCommInitRankConfig: rank 0 nranks 49 total 3.47 (kernels 0.00, alloc 0.00, bootstrap 2.79, allgathers 0.04, topo 0.01, graphs 0.00, connections 0.63, rest 0.00) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=326288, ip=10.128.25.27) ipcDesc 0x40094433fc30
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) CL INFO AllGather: opCount 0 sendbuff 0x4018ee800000 recvbuff 0x401660000000 count 12582912 datatype 9 op 0 root 0 comm 0x400dfaa9fd00 [nranks=4] stream 0x400dfa7c8310
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442310 [0] NCCL INFO AllReduce: opCo
(FSDPPolicyWorkerBase pid=364946) 67c71c0
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO AllReduce: opCount 288 sendbuff 0x400edfa88e00 recvbuff 0x400edfa88e00 count 1 datatyp
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) 0 root 0 comm 0x400e256ca1f0 [nranks=4] stream 0x400e253f6520
(AsyncVLLMInferenceEngine pid=300569, ip=10.128.25.162) (EngineCore_DP0 pid=301120) INFO 06-12 01:05:34 [block_pool.py:452] Successfully reset prefix cache
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO AllReduce: opCount ff sendbuff 0x400edfa88c00 recvbuff 0x400edfa88c00 count 1 datatype 7 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442312 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x40138a400000 recvbuff 0x401760000000 count 155582464 datatype 9 op 0 root 0 comm 0x400e256ca1f0 [nranks=4] stream 0x400e253f6520 [repeated 3044x across cluster]
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442312 [0] NCCL INFO AllReduce: opCount 18f sendbuff 0x400eb9e88c00 recvbuff 0x400eb9e88c00 count 1 datatype 7 op 0 root 0 comm 0x400e252e2e80 [nranks=8] stream (nil) [repeated 1532x across cluster]
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442312 [0] NCCL INFO AllReduce: opCount 18f sendbuff  [repeated 3x across cluster]
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e88c00 recvbuff 0x400e99e88c00 count 1 datatyp
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO AllReduce: opC [repeated 3x across cluster]
(RolloutCoordinator pid=350242, ip=10.128.25.161) [fd-monitor] [01:05:44] OK: 47 / 131,072 FDs open (0.0% of soft limit, hard limit: 131,072)
(RolloutCoordinator pid=350242, ip=10.128.25.161) [fd-monitor] [01:05:44] OK: RSS 0.89 GiB | node mem 381.3/858.0 GiB used (44.4%), avail 476.6 GiB
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) INFO Broadcast: opCount fa sendbuff 0x400e99e2b600 recvbuff 0x400e99e2b600 count 128 datatype 9 op 0 root 0 comm 0x400e092e33d0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442312 [0] NCCL INFO Recv: opCount 0 sendbuff (nil) recvbuff 0x40114a400000 count 155582464 datatype 9 op 0 root 0 comm 0x400e256ca1f0 [nranks=4] stream (nil) [repeated 23x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x400e9fa64200 recvbuff 0x400e9fa88e00 count 1024 datatype 9 op 0 root 0 comm 0x400dfaa9fd00 [nranks=4] strea
(AsyncVLLMInferenceEngine pid=316640, ip=10.128.25.28) tream (nil) [repeated 25x across cluster]
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO AllGather: op [repeated 2x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) 9800000 recvbuff 0x4016d9800000 count 16777216 datatype 9 op 0 root 0 comm 0xaaab0d165c60 [nranks=49] stream (nil) [repeated 31x across cluster]
(AsyncVLLMInferenceEngine pid=305555, ip=10.128.25.164) jpbo-029-36:305972:305972 [0] NCCL INFO Broadcast: opCount a sendbuff 0x40079203c400 recvbuff 0x40079203c400 count 4096 datatype 9 op 0 root 0 comm 0xaaab1d7661e0 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=305555, ip=10.128.25.164) jpbo-029-36:305972:305972 [0] NCCL INFO Broadcast: opCount b sendbuff 0x40079203c400 recvbuff 0x40079203c400 count 4096 datatype 9 op 0 root 0 comm 0xaaab1d7661e0 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=305555, ip=10.128.25.164) jpbo-029-36:305972:305972 [0] NCCL INFO Broadcast: opCount c sendbuff 0x4016f9800000 recvbuff 0x4016f9800000 count 16777216 datatype 9 op 0 root 0 comm 0xaaab1d7661e0 [nranks=49] stream (nil) [repeated 98x across cluster]
(AsyncVLLMInferenceEngine pid=305555, ip=10.128.25.164) jpbo-029-36:305972:305972 [0] NCCL INFO Broadcast: opCount d sendbuff 0x401759200000 recvbuff 0x401759200000 count 4194304 datatype 9 op 0 root 0 comm 0xaaab1d7661e0 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=305555, ip=10.128.25.164) jpbo-029-36:305972:305972 [0] NCCL INFO Broadcast: opCount e sendbuff 0x401759200000 recvbuff 0x401759200000 count 4194304 datatype 9 op 0 root 0 comm 0xaaab1d7661e0 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=305555, ip=10.128.25.164) jpbo-029-36:305972:305972 [0] NCCL INFO Broadcast: opCount f sendbuff 0x4016f9800000 recvbuff 0x4016f9800000 count 16777216 datatype 9 op 0 root 0 comm 0xaaab1d7661e0 [nranks=49] stream (nil) [repeated 98x across cluster]
(FSDPPolicyWorkerBase pid=364944) 4700 [nranks=8] stream (nil) [repeated 88x across cluster]
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) op 0 root 0 comm 0x400e112e5db0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) m 0x400dfa7c8310
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442310 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e89000 recvbuff 0x400e99e89000 count 1 datatype 7 op 0 root
(FSDPPolicyWorkerBase pid=364947) Count 0 sendbuff 0x40133b400000 recvbuff 0x401766000000 count 12582912 datatype 9 op 0 root 0 comm 0x400e416caff0 [nranks=4] stream 0x400e413f9160 [repeated 2x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO AllReduce: opCount 18f sendbuff 0x400eb9e88c00 recvbuff 0x400eb9e88c00 count 1 datatype 7 op 0
(AsyncVLLMInferenceEngine pid=305555, ip=10.128.25.164) jpbo-029-36:305972:305972 [0] NCCL INFO Broadcast: opCount 2a sendbuff 0x401760000000 recvbuff 0x401760000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaab1d7661e0 [nran [repeated 22x across cluster]
(AsyncVLLMInferenceEngine pid=305556, ip=10.128.25.164) jpbo-029-36:305976:305976 [0] NCCL INFO Broadcast: opCount 1c sendbuff 0x401740000000 recvbuff 0x401740000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaab0c5666e0 [nranks=49] s [repeated 24x across cluster]
(AsyncVLLMInferenceEngine pid=443364, ip=10.128.25.174) 0 comm 0xaaab132435a0 [nranks=49] stream (nil) [repeated 24x across cluster]
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442310 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x40138a000000 recvbuff 0x4017 [repeated 10x across cluster]
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) root 0 comm 0x400e092e33d0 [nranks=8] stream (nil) [repeated 5x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x4012e74000
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e89000 recvbuff 0x400e99e89000 count 1 datatype 7 op 0 root 0 comm 0x400e412e5990 [n
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) 66000000 count 12582912 datatype 9 op 0 root 0 comm 0x400e096cb190 [nranks=4] stream 0x400e093f6c80 [repeated 10x across cluster]
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442312 [0] NCCL INFO AllReduce: opCoun
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) jpbo-026-40:249637:249637 [0] NCCL INFO Broadcast: opCount 180 sendbuff 0x40075203c400 recvbuff 0x40075203c400 count 4096 datatype 9 op 0 root 0 comm 0xaaab0d165c60 [nranks=49] stream (nil) [repeated 14484x across cluster]
(AsyncVLLMInferenceEngine pid=301252, ip=10.128.25.163) jpbo-029-35:301664:301664 [0] NCCL INFO Broadcast: opCount fa sendbuff 0x401740000000 recvbuff 0x401740000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaab2ad55ce0 [nranks=49] stream (nil) [repeated 24x across cluster]
(AsyncVLLMInferenceEngine pid=301252, ip=10.128.25.163) jpbo-029-35:301664:301664 [0] NCCL INFO Broadcast: opCount fb sendbuff 0x401740000000 recvbuff 0x401740000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaab2ad55ce0 [nranks=49] stream (nil) [repeated 24x across cluster]
(AsyncVLLMInferenceEngine pid=301252, ip=10.128.25.163) jpbo-029-35:301664:301664 [0] NCCL INFO Broadcast: opCount fc sendbuff 0x40075203c400 recvbuff 0x40075203c400 count 4096 datatype 9 op 0 root 0 comm 0xaaab2ad55ce0 [nranks=49] stream (nil) [repeated 24x across cluster]
(AsyncVLLMInferenceEngine pid=301252, ip=10.128.25.163) jpbo-029-35:301664:301664 [0] NCCL INFO Broadcast: opCount fd sendbuff 0x40075203c400 recvbuff 0x40075203c400 count 4096 datatype 9 op 0 root 0 comm 0xaaab2ad55ce0 [nranks=49] stream (nil) [repeated 24x across cluster]
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e88e00 recvbuff 0x400e99e88e00 count 1 datatype 7 op 0 root 0 comm 0x400e412e4700 [nranks=8] stream (nil) [repeated 1323x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO AllReduce: opCount 1 [repeated 2x across cluster]
(FSDPPolicyWorkerBase pid=364945) 00 recvbuff 0x401766000000 count 12582912 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream 0x400e613efdc0
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x400e99e4e400 recvbuff 0x400e99e88c00 count 32 datatype 9 [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=249225, ip=10.128.25.24) jpbo-026-40:249625:249625 [0] NCCL INFO Broadcast: opCount f6 sendbuff 0x40075203c400 recvbuff 0x40075203c400 count 4096 datatype 9 op 0 root  [repeated 47x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount 157 sendbuff 0x401389580000 recvbuff 0x401389580000 count 4194304 datatype 9 op 0 root 0 comm 0 [repeated 25x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO AllReduce: opCount 22c sendbuff 0x400e9fa88c00 recvbuff 0x400e9fa88c00 count 1 datatype 7 op 0 root 0 comm 0x40 [repeated 5x across cluster]
(FSDPPolicyWorkerBase pid=364944) op 0 root 0 comm 0x400e416cc220 [nranks=4] stream 0x400e413f8020 [repeated 3x across cluster]
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e88c [repeated 3x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:441948 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x4018f0800000 recvbuff 0x401913c00000 count 4194304 datatype 9 op 0 root 0 comm 0x400dfaa9fd0 [repeated 5x across cluster]
(AsyncVLLMInferenceEngine pid=326155, ip=10.128.25.27) ecvbuff 0x40039dd82400 count 128 datatype 9 op 0 root 0 comm 0xaaab0aad8260 [nranks=49] stream (nil) [repeated 24x across cluster]
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) jpbo-029-44:441858:442603 [0] NCCL INFO Broadcast: opCount d7 sendbuff 0x400e9fa88c00 recvbuff 0x400e9fa88c00 count 12 [repeated 24x across cluster]
(AsyncVLLMInferenceEngine pid=305556, ip=10.128.25.164) jpbo-029-36:305976:305976 [0] NCCL INFO Broadcast: opCount 52 sendbuff 0x401740000000 recvbuff 0x401740000000 count 50331648 da [repeated 24x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL  [repeated 2x across cluster]
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442310 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e88c00 recvbuff 0x400e99e88c00 count 1 datatype 7 o
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) 4] stream 0x400e093f6c80 [repeated 7x across cluster]
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) jpbo-029-44:441955:442310 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e88e00 recvbuff 0x400e99e88e00 count 1 datatype 7 op 0 [repeated 2x across cluster]
(FSDPPolicyWorkerBase pid=364946) INFO AllGather: opCount 0 sendbuff 0x4018b1000000 recvbuff 0x401389180000 count 1048576 datatype 9 op 0 root 0 comm 0x400e06a9e080 [nranks=4] stream 0x400e067c71c0
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e88c00 recvbuff 0x400e99e88c00 count 1 datatype 7 op 0 root 0 comm 0x400e412e [repeated 3x across cluster]
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) p 0 root 0 comm 0x400e092e33d0 [nranks=8] stream (nil)
(FSDPPolicyWorkerBase pid=441858, ip=10.128.25.172) 8 datatype 9 op 0 root 0 comm 0x400ef44ecc80 [nranks=49] stream (nil) [repeated 24x across cluster]
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) jpbo-026-43:326772:326772 [0] NCCL INFO Broadcast: opCount aa sendbuff 0x401759200000 recvbuff 0x401759200000 count 4194304 datatype 9 op 0 root 0 comm 0xaaaaf0c213c0 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=326155, ip=10.128.25.27) jpbo-026-43:326770:326770 [0] NCCL INFO Broadcast: opCount ab sendbuff 0x40039dd82400 r [repeated 22x across cluster]
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) tatype 9 op 0 root 0 comm 0xaaaaf0c213c0 [nranks=49] stream (nil) [repeated 24x across cluster]
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) jpbo-026-43:326772:326772 [0] NCCL INFO Broadcast: opCount 6e sendbuff 0x4003ddd82400 recvbuff  [repeated 24x across cluster]
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) jpbo-026-43:326772:326772 [0] NCCL INFO Broadcast: opCount ab sendbuff 0x401759200000 recvbuff 0x401759200000 count 4194304 datatype 9 op 0 root 0 comm 0xaaaaf0c213c0 [nranks=49] stream (nil) [repeated 25x across cluster]
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) jpbo-026-43:326772:326772 [0] NCCL INFO Broadcast: opCount ac sendbuff 0x4016f9800000 recvbuff 0x4016f9800000 count 16777216 datatype 9 op 0 root 0 comm 0xaaaaf0c213c0 [nranks=49] stream (nil) [repeated 48x across cluster]
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) jpbo-029-44:441954:442312 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x400eb9e50a00 recvbuff 0x400eb9e88e00 count 32 datat
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) jpbo-026-43:326772:326772 [0] NCCL INFO Broadcast: opCount ad sendbuff 0x401760000000 recvbuff 0x401760000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaaaf0c213c0 [nranks=49] stream (nil) [repeated 98x across cluster]
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) jpbo-026-43:326772:326772 [0] NCCL INFO Broadcast: opCount ae sendbuff 0x401760000000 recvbuff 0x401760000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaaaf0c213c0 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) jpbo-026-43:326772:326772 [0] NCCL INFO Broadcast: opCount af sendbuff 0x401760000000 recvbuff 0x401760000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaaaf0c213c0 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) jpbo-026-43:326772:326772 [0] NCCL INFO Broadcast: opCount ba sendbuff 0x4016f9800000 recvbuff 0x4016f9800000 count 16777216 datatype 9 op 0 root 0 comm 0xaaaaf0c213c0 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=301252, ip=10.128.25.163) jpbo-029-35:301664:301664 [ [repeated 23x across cluster]
(FSDPPolicyWorkerBase pid=441955, ip=10.128.25.172) ount fe sendbuff 0x400e99e88c00 recvbuff 0x400e99e88c00 count 1 datatype 7 op 0 root 0 comm 0x400e092e33d0 [nranks=8] stream (nil)
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) jpbo-026-43:326772:326772 [0] NCCL INFO Broadcast: opCount bb sendbuff 0x401760000000 recvbuff 0x401760000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaaaf0c213c0 [nranks=49] stream (nil) [repeated 98x across cluster]
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) jpbo-026-43:326772:326772 [0] NCCL INFO Broadcast: opCount bc sendbuff 0x401760000000 recvbuff 0x401760000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaaaf0c213c0 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) jpbo-026-43:326772:326772 [0] NCCL INFO Broadcast: opCount bd sendbuff 0x401760000000 recvbuff 0x401760000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaaaf0c213c0 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) jpbo-026-43:326772:326772 [0] NCCL INFO Broadcast: opCount be sendbuff 0x4016f9800000 recvbuff 0x4016f9800000 count 16777216 datatype 9 op 0 root 0 comm 0xaaaaf0c213c0 [nranks=49] stream (nil) [repeated 98x across cluster]
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) jpbo-026-43:326772:326772 [0] NCCL INFO Broadcast: opCount bf sendbuff 0x401759200000 recvbuff 0x401759200000 count 4194304 datatype 9 op 0 root 0 comm 0xaaaaf0c213c0 [nranks=49] stream (nil) [repeated 48x across cluster]
(FSDPPolicyWorkerBase pid=364946) jpbo-026-33:364946:365413 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x4018c2000000 recvbuff 0x401932a00000 count 4194304 datatype 9 op 0 root 0 comm 0x400e06a9e080 [n
(FSDPPolicyWorkerBase pid=441954, ip=10.128.25.172) ype 9 op 0 root 0 comm 0x400e256ca1f0 [nranks=4] stream 0x400e253f6520
(AsyncVLLMInferenceEngine pid=304566, ip=10.128.25.165) jpbo-029-37:304984:304984 [0] NCCL INFO Broadcast: opCount ca sendbuff 0x401720000000 recvbuff 0x401720000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaab3136e390 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=304566, ip=10.128.25.165) jpbo-029-37:304984:304984 [0] NCCL INFO Broadcast: opCount cb sendbuff 0x401720000000 recvbuff 0x401720000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaab3136e390 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=304566, ip=10.128.25.165) jpbo-029-37:304984:304984 [0] NCCL INFO Broadcast: opCount cc sendbuff 0x4016b9800000 recvbuff 0x4016b9800000 count 16777216 datatype 9 op 0 root 0 comm 0xaaab3136e390 [nranks=49] stream (nil) [repeated 98x across cluster]
(AsyncVLLMInferenceEngine pid=304566, ip=10.128.25.165) jpbo-029-37:304984:304984 [0] NCCL INFO Broadcast: opCount cd sendbuff 0x401719200000 recvbuff 0x401719200000 count 4194304 datatype 9 op 0 root 0 comm 0xaaab3136e390 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=304566, ip=10.128.25.165) jpbo-029-37:304984:304984 [0] NCCL INFO Broadcast: opCount ce sendbuff 0x401719200000 recvbuff 0x401719200000 count 4194304 datatype 9 op 0 root 0 comm 0xaaab3136e390 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=304566, ip=10.128.25.165) jpbo-029-37:304984:304984 [0] NCCL INFO Broadcast: opCount cf sendbuff 0x4016b9800000 recvbuff 0x4016b9800000 count 16777216 datatype 9 op 0 root 0 comm 0xaaab3136e390 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=326155, ip=10.128.25.27) jpbo-026-43:326770:326770 [0] NCCL INFO Broadcast: opCo [repeated 22x across cluster]
(FSDPPolicyWorkerBase pid=364946) count 1 datatype 7 op 0 root 0 comm 0x400e066b2ed0 [nranks=8] stream (nil) [repeated 26x across cluster]
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) jpbo-026-43:326772:326772 [0] NCCL INFO Broadcast: opCount 8a s [repeated 24x across cluster]
(AsyncVLLMInferenceEngine pid=304566, ip=10.128.25.165) jpbo-029-37:304984:304984 [0] NCCL INFO Broadcast: opCount da sendbuff 0x40075203c400 recvbuff 0x40075203c400 count 4096 datatype 9 op 0 root 0 comm 0xaaab3136e390 [nranks=49] stream (nil) [repeated 73x across cluster]
(AsyncVLLMInferenceEngine pid=249225, ip=10.128.25.24) jpbo-026-40:249625:249625 [0] NCCL INFO Broadcast: opCount db sendbuff 0x401719200000 recvbuff 0x401719200000 count 4194304 datatype 9 op 0 root 0 comm 0xaaab168db1e0 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=249225, ip=10.128.25.24) jpbo-026-40:249625:249625 [0] NCCL INFO Broadcast: opCount dc sendbuff 0x401719200000 recvbuff 0x401719200000 count 4194304 datatype 9 op 0 root 0 comm 0xaaab168db1e0 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=249225, ip=10.128.25.24) jpbo-026-40:249625:249625 [0] NCCL INFO Broadcast: opCount dd sendbuff 0x4016b9800000 recvbuff 0x4016b9800000 count 16777216 datatype 9 op 0 root 0 comm 0xaaab168db1e0 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=249225, ip=10.128.25.24) jpbo-026-40:249625:249625 [0] NCCL INFO Broadcast: opCount de sendbuff 0x401720000000 recvbuff 0x401720000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaab168db1e0 [nranks=49] stream (nil) [repeated 98x across cluster]
(AsyncVLLMInferenceEngine pid=249225, ip=10.128.25.24) jpbo-026-40:249625:249625 [0] NCCL INFO Broadcast: opCount df sendbuff 0x401720000000 recvbuff 0x401720000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaab168db1e0 [nranks=49] stream (nil) [repeated 48x across cluster]
(FSDPPolicyWorkerBase pid=364945) 8f sendbuff 0x400eb9e88c00 recvbuff 0x400eb9e88c00 count 1 datatype 7 op 0 root 0 comm 0x400e612dc480 [nranks=8] stream (nil)
(AsyncVLLMInferenceEngine pid=249225, ip=10.128.25.24) jpbo-026-40:249625:249625 [0] NCCL INFO Broadcast: opCount ea sendbuff 0x401719200000 recvbuff 0x401719200000 count 4194304 datatype 9 op 0 root 0 comm 0xaaab168db1e0 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=249225, ip=10.128.25.24) jpbo-026-40:249625:249625 [0] NCCL INFO Broadcast: opCount eb sendbuff 0x4016b9800000 recvbuff 0x4016b9800000 count 16777216 datatype 9 op 0 root 0 comm 0xaaab168db1e0 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=249225, ip=10.128.25.24) jpbo-026-40:249625:249625 [0] NCCL INFO Broadcast: opCount ec sendbuff 0x401720000000 recvbuff 0x401720000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaab168db1e0 [nranks=49] stream (nil) [repeated 98x across cluster]
(AsyncVLLMInferenceEngine pid=249225, ip=10.128.25.24) jpbo-026-40:249625:249625 [0] NCCL INFO Broadcast: opCount ed sendbuff 0x401720000000 recvbuff 0x401720000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaab168db1e0 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=249225, ip=10.128.25.24) jpbo-026-40:249625:249625 [0] NCCL INFO Broadcast: opCount ee sendbuff 0x401720000000 recvbuff 0x401720000000 count 50331648 datatype 9 op 0 root 0 comm 0xaaab168db1e0 [nranks=49] stream (nil) [repeated 48x across cluster]
(AsyncVLLMInferenceEngine pid=249225, ip=10.128.25.24) jpbo-026-40:249625:249625 [0] NCCL INFO Broadcast: opCount ef sendbuff 0x4016b9800000 recvbuff 0x4016b9800000 count 16777216 datatype 9 op 0 root 0 comm 0xaaab168db1e0 [nranks=49] stream (nil) [repeated 98x across cluster]
(FSDPPolicyWorkerBase pid=364945) jpbo-026-33:364945:365415 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x401342a00000 recvbuff 0x40171a400000 count
(AsyncVLLMInferenceEngine pid=301252, ip=10.128.25.163) unt d6 sendbuff 0x4003bdd82400 recvbuff 0x4003bdd82400 count 128 datatype 9 op 0 root 0 comm 0xaaab2ad55ce0 [nranks=49] stream (nil) [repeated 22x across cluster]
(AsyncVLLMInferenceEngine pid=301252, ip=10.128.25.163) jpbo-029-35:301664:301664 [0] NCCL INFO Broadcast: opCount fe sendbuff 0x4016d9800000 recvbuff 0x4016d9800000 count 16777216 datatype 9 op 0 root 0 comm 0xaaab2ad55ce0 [nranks=49] stream (nil) [repeated 23x across cluster]
(AsyncVLLMInferenceEngine pid=301252, ip=10.128.25.163) jpbo-029-35:301664:301664 [0] NCCL INFO Broadcast: opCount ff sendbuff 0x401739200000 recvbuff 0x401739200000 count 4194304 datatype 9 op 0 root 0 comm 0xaaab2ad55ce0 [nranks=49] stream (nil) [repeated 23x across cluster]
(AsyncVLLMInferenceEngine pid=301251, ip=10.128.25.163) endbuff 0x4003ddd82400 recvbuff 0x4003ddd82400 count 128 datatype 9 op 0 root 0 comm 0xaaab3afe1e00 [nranks=49] stream (nil) [repeated 24x across cluster]
(AsyncVLLMInferenceEngine pid=301251, ip=10.128.25.163) jpbo-029-35:301662:301662 [0] NCCL I [repeated 24x across cluster]
(FSDPPolicyWorkerBase pid=364945) 1048576 datatype 9 op 0 root 0 comm 0x400e616c3ee0 [nranks=4] stream 0x400e613efdc0
(FSDPPolicyWorkerBase pid=441953, ip=10.128.25.172) jpbo-029-44:441953:442311 [0] NCCL INFO AllReduce: op
(FSDPPolicyWorkerBase pid=364947) jpbo-026-33:364947:365414 [0] NCCL INFO AllGat
(AsyncVLLMInferenceEngine pid=316639, ip=10.128.25.28) jpbo-026-44:317124:317124 [0] NCCL INFO Broadcast: opCount 12b sendbuff 0x401739200000 recvbuff 0x401739200000 count 4194304 datatype 9 op 0 root 0 c [repeated 22x across cluster]
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) NFO Broadcast: opCount a5 sendbuff 0x4016f9800000 recvbuff 0x4016f9800000 count 16777216 datatype 9 op 0 root 0 comm 0xaaaaf0c213c0 [nranks=49] stream (nil) [repeated 24x across cluster]
(FSDPPolicyWorkerBase pid=364947) her: opCount 0 sendbuff 0x400e99e53200 recvbuff 0x400e99e88e00 count 32 datatype 9 op 0 root 0 comm 0x400e416caff0 [nranks=4] stream 0x400e413f9160
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) omm 0xaaab5583a610 [nranks=49] stream (nil) [repeated 22x across cluster]
(AsyncVLLMInferenceEngine pid=304567, ip=10.128.25.165) jpbo-029-37:304986:304986 [0] NCCL INFO Broadcast: opCount 156 sendbuff 0x4016f [repeated 22x across cluster]
(AsyncVLLMInferenceEngine pid=304566, ip=10.128.25.165) jpbo-029-37:304984:304984 [0] NCCL INFO Broadcast: opCount da sendbuff 0x4016b9800000 recvbuff 0x4016b9800000 count 16777216 datatype 9 op 0 root 0 comm 0xaaab3136e390 [nran [repeated 24x across cluster]
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO AllReduce: opCount fe sendbuff 0x400e99e88c00 recvbuff 0x400e99e88c00 count 1 datatype
(FSDPPolicyWorkerBase pid=364945) jpbo
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) jpbo- [repeated 22x across cluster]
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) (EngineCore_DP0 pid=316475) INFO 06-12 01:05:34 [block_pool.py:452] Successfully reset prefix cache [repeated 47x across cluster]
(FSDPPolicyWorkerBase pid=364944) jpbo-026-33:364944:365416 [0] NCCL INFO AllGather: opCount 0 sendbuff 0x4013a0000000 recvbuff 0x401760000000 count 155582464 datatype 9 op 0 root 0 comm 0x400e416cc220 [nranks=4] stream 0x400e413f8020 [repeated 42x across cluster]
(RolloutCoordinator pid=479438, ip=10.128.25.176) [fd-monitor] [01:05:51] OK: 47 / 131,072 FDs open (0.0% of soft limit, hard limit: 131,072)
(RolloutCoordinator pid=479438, ip=10.128.25.176) [fd-monitor] [01:05:51] OK: RSS 0.89 GiB | node mem 368.5/858.0 GiB used (42.9%), avail 489.5 GiB
(RolloutCoordinator pid=301361, ip=10.128.25.162) [fd-monitor] [01:05:58] OK: 47 / 131,072 FDs open (0.0% of soft limit, hard limit: 131,072)
(RolloutCoordinator pid=301361, ip=10.128.25.162) [fd-monitor] [01:05:58] OK: RSS 0.89 GiB | node mem 379.8/858.0 GiB used (44.3%), avail 478.2 GiB
(RolloutCoordinator pid=380389, ip=10.128.25.25) [fd-monitor] [01:06:07] OK: 47 / 131,072 FDs open (0.0% of soft limit, hard limit: 131,072) [repeated 2x across cluster]
(RolloutCoordinator pid=380389, ip=10.128.25.25) [fd-monitor] [01:06:07] OK: RSS 0.89 GiB | node mem 389.9/858.0 GiB used (45.4%), avail 468.0 GiB [repeated 2x across cluster]
(RolloutCoordinator pid=350242, ip=10.128.25.161) [fd-monitor] [01:07:44] OK: 47 / 131,072 FDs open (0.0% of soft limit, hard limit: 131,072)
(RolloutCoordinator pid=350242, ip=10.128.25.161) [fd-monitor] [01:07:44] OK: RSS 0.89 GiB | node mem 381.5/858.0 GiB used (44.5%), avail 476.5 GiB
(RolloutCoordinator pid=479438, ip=10.128.25.176) [fd-monitor] [01:07:51] OK: 47 / 131,072 FDs open (0.0% of soft limit, hard limit: 131,072)
(RolloutCoordinator pid=479438, ip=10.128.25.176) [fd-monitor] [01:07:51] OK: RSS 0.89 GiB | node mem 368.5/858.0 GiB used (43.0%), avail 489.4 GiB
(RolloutCoordinator pid=301361, ip=10.128.25.162) [fd-monitor] [01:07:58] OK: 47 / 131,072 FDs open (0.0% of soft limit, hard limit: 131,072)
(RolloutCoordinator pid=301361, ip=10.128.25.162) [fd-monitor] [01:07:58] OK: RSS 0.89 GiB | node mem 379.9/858.0 GiB used (44.3%), avail 478.0 GiB
(skyrl_entrypoint pid=364638) [fd-monitor] [01:08:01] OK: 104 / 131,072 FDs open (0.1% of soft limit, hard limit: 131,072)
(skyrl_entrypoint pid=364638) [fd-monitor] [01:08:01] OK: RSS 1.74 GiB | node mem 245.2/858.0 GiB used (28.6%), avail 612.8 GiB
(RolloutCoordinator pid=380389, ip=10.128.25.25) [fd-monitor] [01:08:07] OK: 47 / 131,072 FDs open (0.0% of soft limit, hard limit: 131,072)
(RolloutCoordinator pid=380389, ip=10.128.25.25) [fd-monitor] [01:08:07] OK: RSS 0.89 GiB | node mem 390.0/858.0 GiB used (45.5%), avail 468.0 GiB
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161) Provider List: https://docs.litellm.ai/docs/providers [repeated 3x across cluster]
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161) Provider List: https://docs.litellm.ai/docs/providers [repeated 714x across cluster]
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers [repeated 797x across cluster]
(AsyncVLLMInferenceEngine pid=326289, ip=10.128.25.27) INFO 06-12 01:09:13 [hf.py:318] Detected the chat template content format to be 'string'. You can set `--chat-template-content-format` to override this.
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) INFO 06-12 01:09:18 [loggers.py:259] Engine 000: Avg prompt throughput: 2.5 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 0.0%
(AsyncVLLMInferenceEngine pid=305555, ip=10.128.25.164) INFO 06-12 01:09:17 [hf.py:318] Detected the chat template content format to be 'string'. You can set `--chat-template-content-format` to override this. [repeated 9x across cluster]
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) INFO 06-12 01:09:23 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 52.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.4%, Prefix cache hit rate: 0.0% [repeated 14x across cluster]
(AsyncVLLMInferenceEngine pid=301251, ip=10.128.25.163) INFO 06-12 01:09:23 [hf.py:318] Detected the chat template content format to be 'string'. You can set `--chat-template-content-format` to override this. [repeated 9x across cluster]
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) INFO 06-12 01:09:28 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 50.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.5%, Prefix cache hit rate: 0.0% [repeated 21x across cluster]
(AsyncVLLMInferenceEngine pid=249097, ip=10.128.25.24) INFO 06-12 01:09:25 [hf.py:318] Detected the chat template content format to be 'string'. You can set `--chat-template-content-format` to override this. [repeated 4x across cluster]
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) INFO 06-12 01:09:33 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 52.2 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.5%, Prefix cache hit rate: 0.0% [repeated 29x across cluster]
(AsyncVLLMInferenceEngine pid=300699, ip=10.128.25.162) INFO 06-12 01:09:31 [hf.py:318] Detected the chat template content format to be 'string'. You can set `--chat-template-content-format` to override this. [repeated 6x across cluster]
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) INFO 06-12 01:09:38 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 54.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.6%, Prefix cache hit rate: 0.0% [repeated 30x across cluster]
(AsyncVLLMInferenceEngine pid=305556, ip=10.128.25.164) INFO 06-12 01:09:34 [hf.py:318] Detected the chat template content format to be 'string'. You can set `--chat-template-content-format` to override this. [repeated 2x across cluster]
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) INFO 06-12 01:09:43 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 54.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.7%, Prefix cache hit rate: 0.0% [repeated 28x across cluster]
(RolloutCoordinator pid=350242, ip=10.128.25.161) [fd-monitor] [01:09:44] OK: 263 / 131,072 FDs open (0.2% of soft limit, hard limit: 131,072)
(RolloutCoordinator pid=350242, ip=10.128.25.161) [fd-monitor] [01:09:44] OK: RSS 1.13 GiB | node mem 382.1/858.0 GiB used (44.5%), avail 475.9 GiB
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) INFO 06-12 01:09:48 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 54.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.8%, Prefix cache hit rate: 0.0% [repeated 31x across cluster]
(RolloutCoordinator pid=479438, ip=10.128.25.176) [fd-monitor] [01:09:51] OK: 263 / 131,072 FDs open (0.2% of soft limit, hard limit: 131,072)
(RolloutCoordinator pid=479438, ip=10.128.25.176) [fd-monitor] [01:09:51] OK: RSS 1.13 GiB | node mem 369.2/858.0 GiB used (43.0%), avail 488.8 GiB
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) INFO 06-12 01:09:53 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 54.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.9%, Prefix cache hit rate: 0.0% [repeated 31x across cluster]
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) INFO 06-12 01:09:58 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 54.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.9%, Prefix cache hit rate: 0.0% [repeated 28x across cluster]
(RolloutCoordinator pid=301361, ip=10.128.25.162) [fd-monitor] [01:09:58] OK: 215 / 131,072 FDs open (0.2% of soft limit, hard limit: 131,072)
(RolloutCoordinator pid=301361, ip=10.128.25.162) [fd-monitor] [01:09:58] OK: RSS 1.07 GiB | node mem 380.3/858.0 GiB used (44.3%), avail 477.7 GiB
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) INFO 06-12 01:10:03 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 54.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.0%, Prefix cache hit rate: 0.0% [repeated 29x across cluster]
(skyrl_entrypoint pid=364638) [fd-monitor] [01:10:01] OK: 177 / 131,072 FDs open (0.1% of soft limit, hard limit: 131,072)
(skyrl_entrypoint pid=364638) [fd-monitor] [01:10:01] OK: RSS 1.76 GiB | node mem 245.3/858.0 GiB used (28.6%), avail 612.7 GiB
(RolloutCoordinator pid=380389, ip=10.128.25.25) [fd-monitor] [01:10:07] OK: 215 / 131,072 FDs open (0.2% of soft limit, hard limit: 131,072)
(RolloutCoordinator pid=380389, ip=10.128.25.25) [fd-monitor] [01:10:07] OK: RSS 1.07 GiB | node mem 390.6/858.0 GiB used (45.5%), avail 467.4 GiB
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) INFO 06-12 01:10:08 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 54.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.1%, Prefix cache hit rate: 0.0% [repeated 28x across cluster]
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) INFO 06-12 01:10:13 [loggers.py:259] Engine 000: Avg prompt throughput: 190.6 tokens/s, Avg generation throughput: 26.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.4%, Prefix cache hit rate: 64.5% [repeated 27x across cluster]
(AsyncVLLMInferenceEngine pid=301252, ip=10.128.25.163) INFO 06-12 01:10:16 [hf.py:318] Detected the chat template content format to be 'string'. You can set `--chat-template-content-format` to override this.
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(RolloutCoordinator pid=479438, ip=10.128.25.176) Provider List: https://docs.litellm.ai/docs/providers
(RolloutCoordinator pid=479438, ip=10.128.25.176)
(AsyncVLLMInferenceEngine pid=316189, ip=10.128.25.23) INFO 06-12 01:10:18 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 54.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.5%, Prefix cache hit rate: 64.5% [repeated 30x across cluster]
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(RolloutCoordinator pid=350242, ip=10.128.25.161)
(AsyncVLLMInferenceEngine pid=379731, ip=10.128.25.25) INFO 06-12 01:10:18 [hf.py:318] Detected the chat template content format to be 'string'. You can set `--chat-template-content-format` to override this. [repeated 4x across cluster]
(RolloutCoordinator pid=350242, ip=10.128.25.161) Provider List: https://docs.litellm.ai/docs/providers [repeated 3x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) INFO 06-12 01:10:23 [loggers.py:259] Engine 000: Avg prompt throughput: 57.1 tokens/s, Avg generation throughput: 83.4 tokens/s, Running: 2 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.9%, Prefix cache hit rate: 80.3% [repeated 27x across cluster]
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(RolloutCoordinator pid=380389, ip=10.128.25.25)
(AsyncVLLMInferenceEngine pid=443104, ip=10.128.25.174) INFO 06-12 01:10:27 [hf.py:318] Detected the chat template content format to be 'string'. You can set `--chat-template-content-format` to override this.
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162)
(RolloutCoordinator pid=301361, ip=10.128.25.162) Provider List: https://docs.litellm.ai/docs/providers [repeated 4x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) INFO 06-12 01:10:28 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 56.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.1%, Prefix cache hit rate: 80.3% [repeated 26x across cluster]
(AsyncVLLMInferenceEngine pid=316640, ip=10.128.25.28) INFO 06-12 01:10:31 [hf.py:318] Detected the chat template content format to be 'string'. You can set `--chat-template-content-format` to override this. [repeated 5x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) INFO 06-12 01:10:33 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 51.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.2%, Prefix cache hit rate: 80.3% [repeated 35x across cluster]
(AsyncVLLMInferenceEngine pid=478789, ip=10.128.25.176) INFO 06-12 01:10:34 [hf.py:318] Detected the chat template content format to be 'string'. You can set `--chat-template-content-format` to override this. [repeated 2x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) INFO 06-12 01:10:38 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 51.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.3%, Prefix cache hit rate: 80.3% [repeated 41x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) INFO 06-12 01:10:43 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 51.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.3%, Prefix cache hit rate: 80.3% [repeated 40x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) INFO 06-12 01:10:48 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 50.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.4%, Prefix cache hit rate: 80.3% [repeated 40x across cluster]
(AsyncVLLMInferenceEngine pid=249226, ip=10.128.25.24) INFO 06-12 01:10:53 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 50.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.5%, Prefix cache hit rate: 80.3% [repeated 38x across cluster]
(AsyncVLLMInferenceEngine pid=443232, ip=10.128.25.174) INFO 06-12 01:10:56 [loggers.py:259] Engine 000: Avg prompt throughput: 64.7 tokens/s, Avg generation throughput: 77.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.8%, Prefix cache hit rate: 68.0% [repeated 21x across cluster]
Error executing job with overrides: ['+terminal_bench_config=terminal_bench', 'trainer.strategy=fsdp2', 'trainer.algorithm.advantage_estimator=rloo_n', 'trainer.algorithm.use_kl_loss=false', 'trainer.algorithm.kl_loss_coef=0.0', 'trainer.algorithm.eps_clip_low=0.2', 'trainer.algorithm.eps_clip_high=0.05', 'trainer.algorithm.loss_reduction=seq_mean_token_sum_norm_global', 'trainer.algorithm.use_tis=true', 'trainer.algorithm.tis_imp_ratio_cap=2.0', 'trainer.epochs=2', 'trainer.max_steps=80', 'trainer.update_epochs_per_batch=1', 'trainer.train_batch_size=64', 'trainer.policy_mini_batch_size=64', 'trainer.eval_batch_size=64', 'trainer.micro_forward_batch_size_per_gpu=4', 'trainer.micro_train_batch_size_per_gpu=1', 'trainer.max_prompt_length=999999', 'trainer.eval_interval=999999', 'trainer.eval_before_train=false', 'trainer.ckpt_interval=2', 'trainer.resume_mode=latest', 'trainer.hf_save_interval=5', '++trainer.hf_hub_repo_id=laion/explore-tis-untrunc', '++trainer.hf_hub_private=false', '++trainer.hf_hub_revision=main', '++trainer.enable_db_registration=false', 'trainer.project_name=OpenThoughts-Agent', 'trainer.log_level=INFO', 'trainer.tracker_commit_each_step=true', 'trainer.logger=console', 'trainer.run_name=explore-tis-untrunc', 'trainer.ckpt_path=/e/data1/datasets/playground/ot-baf/explore-tis-untrunc/explore-tis-untrunc/checkpoints', 'trainer.export_path=/e/data1/datasets/playground/ot-baf/explore-tis-untrunc/explore-tis-untrunc/exports', 'trainer.policy.optimizer_config.lr=8e-6', 'trainer.policy.optimizer_config.weight_decay=0.0', 'trainer.policy.optimizer_config.adam_betas=[0.9,0.999]', 'trainer.policy.optimizer_config.max_grad_norm=0.9', 'trainer.policy.fsdp_config.cpu_offload=false', 'trainer.policy.fsdp_config.reshard_after_forward=true', 'trainer.policy.fsdp_config.fsdp_size=4', 'trainer.policy.model.path=/e/data1/datasets/playground/ot-baf/hf_hub/models--laion--GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/snapshots/0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6', 'trainer.ref.fsdp_config.cpu_offload=false', 'trainer.ref.fsdp_config.reshard_after_forward=true', 'trainer.ref.fsdp_config.fsdp_size=4', 'trainer.placement.colocate_all=false', 'trainer.placement.policy_num_nodes=2', 'trainer.placement.ref_num_nodes=2', 'trainer.placement.policy_num_gpus_per_node=4', 'trainer.placement.ref_num_gpus_per_node=4', 'trainer.fully_async.max_staleness_steps=16', 'trainer.fully_async.num_parallel_generation_workers=338', 'generator.backend=vllm', 'generator.timeout_multiplier=1.0', 'generator.model_dtype=bfloat16', 'generator.inference_engine_tensor_parallel_size=1', 'generator.num_inference_engines=48', 'generator.n_samples_per_prompt=8', 'generator.eval_n_samples_per_prompt=8', 'generator.gpu_memory_utilization=0.75', 'generator.max_num_seqs=24', 'generator.max_num_batched_tokens=65536', 'generator.enable_prefix_caching=true', 'generator.enable_chunked_prefill=true', 'generator.run_engines_locally=true', 'generator.weight_sync_backend=nccl', 'generator.async_engine=true', 'generator.batched=false', 'generator.enable_http_endpoint=true', 'generator.enable_ray_prometheus_stats=false', 'generator.vllm_stats_interval=1', 'generator.append_eos_token_after_stop_str_in_multi_turn=true', 'generator.max_turns=999999', 'generator.sampling_params.max_generate_length=4096', 'generator.sampling_params.temperature=0.7', 'generator.sampling_params.top_p=0.95', 'generator.sampling_params.top_k=20', '++generator.engine_init_kwargs.max_model_len=32768', '++generator.engine_init_kwargs.custom_chat_template_chat_completion_path=chat_templates/qwen3_thinking_acc.jinja2', '++generator.engine_init_kwargs.served_model_name=0e3bff0c4e51f6b9ec0713b98b9eec36efb91cc6', 'data.train_data=["/e/scratch/jureap59/feuer1/tasks/exp_rpt_pymethods2test-large"]', 'data.val_data=[]', '+terminal_bench_config.trials_dir=/e/data1/datasets/playground/ot-baf/explore-tis-untrunc/explore-tis-untrunc/trace_jobs', '+terminal_bench_config.harbor.name=terminus-2', '+terminal_bench_config.harbor.max_episodes=999999', '+terminal_bench_config.harbor.enable_summarize=false', '+terminal_bench_config.harbor.store_all_messages=true', '+terminal_bench_config.harbor.trajectory_config.raw_content=true', '+terminal_bench_config.harbor.enable_episode_logging=false', '+terminal_bench_config.harbor.record_terminal_session=false', '+terminal_bench_config.harbor.enable_pane_logging=false', '+terminal_bench_config.harbor.strict_json_parser=true', '+terminal_bench_config.harbor.interleaved_thinking=true', '+terminal_bench_config.harbor.extra_body.chat_template_kwargs.enable_thinking=true', '+terminal_bench_config.harbor.override_timeout_sec=900', '+terminal_bench_config.harbor.override_cpus=1', '+terminal_bench_config.harbor.override_memory_mb=2048', '+terminal_bench_config.harbor.override_storage_mb=2048', '+terminal_bench_config.harbor.auto_snapshot=true', '+terminal_bench_config.harbor.verifier_override_timeout_sec=120', '+terminal_bench_config.harbor.max_retries=3', '+terminal_bench_config.harbor.min_wait_sec=60.0', '+terminal_bench_config.harbor.max_wait_sec=600.0', '+terminal_bench_config.harbor.wait_multiplier=2.0', '+terminal_bench_config.harbor.exclude_exceptions=["VerifierTimeoutError","VerifierRuntimeError","RewardFileNotFoundError","RewardFileEmptyError","VerifierOutputParseError"]', '+terminal_bench_config.harbor.n_concurrent_trials=675', '+terminal_bench_config.harbor.log_level=INFO', '+terminal_bench_config.harbor.enable_reward_shaping=false', '+terminal_bench_config.harbor.collect_rollout_details=true', '+terminal_bench_config.harbor.enable_error_classification=true', '+terminal_bench_config.harbor.mask_exceptions=["DaytonaError","EnvironmentStartTimeoutError","NetworkError","ConnectionError","RewardFileNotFoundError","RewardFileEmptyError","AgentEnvironmentTimeoutError","ContextLengthExceededError"]', '+terminal_bench_config.harbor.default_error_treatment=zero', '+terminal_bench_config.harbor.passthrough_exceptions=["AgentTimeoutError"]', '+terminal_bench_config.harbor.zero_exceptions=[]', '+terminal_bench_config.model_info.max_input_tokens=32000', '+terminal_bench_config.model_info.max_output_tokens=4096', '+terminal_bench_config.archiving.enabled=false', '+terminal_bench_config.trace_upload.enabled=true', '+terminal_bench_config.trace_upload.repo_org=DCAgent', '+terminal_bench_config.trace_upload.episodes=last', '+terminal_bench_config.trace_upload.dataset_type=SFT', '+terminal_bench_config.trace_upload.cleanup=true', 'generator.sampling_params.temperature=1.0', 'generator.sampling_params.top_p=1.0', 'generator.sampling_params.top_k=-1']
Traceback (most recent call last):
File "<frozen runpy>", line 198, in _run_module_as_main
File "<frozen runpy>", line 88, in _run_code
File "/e/scratch/jureap59/feuer1/OpenThoughts-Agent/SkyRL/skyrl-train/examples/terminal_bench/entrypoints/main_tbench.py", line 142, in <module>
main()
File "/e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/hydra/main.py", line 94, in decorated_main
_run_hydra(
File "/e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra
_run_app(
File "/e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/hydra/_internal/utils.py", line 457, in _run_app
run_and_report(
File "/e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/hydra/_internal/utils.py", line 223, in run_and_report
raise ex
File "/e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/hydra/_internal/utils.py", line 220, in run_and_report
return func()
^^^^^^
File "/e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/hydra/_internal/utils.py", line 458, in <lambda>
lambda: hydra.run(
^^^^^^^^^^
File "/e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/hydra/_internal/hydra.py", line 132, in run
_ = ret.return_value
^^^^^^^^^^^^^^^^
File "/e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/hydra/core/utils.py", line 260, in return_value
raise self._return_value
File "/e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/hydra/core/utils.py", line 186, in run_job
ret.return_value = task_function(task_cfg)
^^^^^^^^^^^^^^^^^^^^^^^
File "/e/scratch/jureap59/feuer1/OpenThoughts-Agent/SkyRL/skyrl-train/examples/terminal_bench/entrypoints/main_tbench.py", line 132, in main
ray.get(skyrl_entrypoint.remote(cfg))
File "/e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/ray/_private/auto_init_hook.py", line 22, in auto_init_wrapper
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/ray/_private/client_mode_hook.py", line 104, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/ray/_private/worker.py", line 2967, in get
values, debugger_breakpoint = worker.get_objects(
^^^^^^^^^^^^^^^^^^^
File "/e/scratch/jureap59/feuer1/OpenThoughts-Agent/envs/rl/lib/python3.12/site-packages/ray/_private/worker.py", line 1017, in get_objects
raise value
ray.exceptions.NodeDiedError: Task failed because the node it was running on is dead or unavailable. Node IP: 10.128.25.17, node ID: 96706d0fc7d05b397467667c5e336ac21712cf7e0c8bf1b2f4037765. This can happen if the node was preempted, had a hardware failure, or its raylet crashed unexpectedly. To see node death information, use `ray list nodes --filter node_id=96706d0fc7d05b397467667c5e336ac21712cf7e0c8bf1b2f4037765`, check the Ray dashboard cluster page, search the node ID in the GCS logs, or use `ray logs raylet.out -ip 10.128.25.17`.
Stopping Ray cluster...
Ray cluster stopped
[RLJobRunner] Crash detected (exit!=0) — preserving Ray logs to /e/data1/datasets/playground/ot-baf/explore-tis-untrunc/explore-tis-untrunc/ray_logs BEFORE trace upload (so a wall-clock kill can't lose crash evidence)...