145 lines
20 KiB
Plaintext
145 lines
20 KiB
Plaintext
/usr/local/corex/lib/python3/dist-packages/torch/cuda/__init__.py:51: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
|
||
import pynvml # type: ignore[import]
|
||
INFO 07-14 17:13:44 importing.py:10] Triton not installed; certain GPU-related functions will not be available.
|
||
2026-07-14 17:13:46.085639: I tensorflow/core/util/port.cc:110] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
||
2026-07-14 17:13:46.136960: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
||
To enable the following instructions: SSE3 SSE4.1 SSE4.2 AVX AVX2 AVX512F AVX512_VNNI AVX512_BF16 AVX_VNNI AMX_TILE AMX_INT8 AMX_BF16 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
||
WARNING:tensorflow:Deprecation warnings have been disabled. Set TF_ENABLE_DEPRECATION_WARNINGS=1 to re-enable them.
|
||
INFO 07-14 17:13:52 api_server.py:530] vLLM API server version 0.6.3
|
||
INFO 07-14 17:13:52 api_server.py:531] args: Namespace(host='0.0.0.0', port=1111, uvicorn_log_level='info', allow_credentials=False, allowed_origins=['*'], allowed_methods=['*'], allowed_headers=['*'], api_key=None, lora_modules=None, prompt_adapters=None, chat_template=None, response_role='assistant', ssl_keyfile=None, ssl_certfile=None, ssl_ca_certs=None, ssl_cert_reqs=0, root_path=None, middleware=[], return_tokens_as_token_ids=False, disable_frontend_multiprocessing=True, enable_auto_tool_choice=True, tool_call_parser='qwen3_coder', tool_parser_plugin='', reasoning_parser='qwen3', model='/root/public-storage/models/Qwen/Qwen3.6-35B-A3B', tokenizer=None, skip_tokenizer_init=False, revision=None, code_revision=None, tokenizer_revision=None, tokenizer_mode='auto', trust_remote_code=True, download_dir=None, load_format='auto', config_format='auto', dtype='auto', kv_cache_dtype='auto', quantization_param_path=None, max_model_len=100000, guided_decoding_backend='outlines', distributed_executor_backend=None, worker_use_ray=False, pipeline_parallel_size=1, tensor_parallel_size=4, max_parallel_loading_workers=None, ray_workers_use_nsight=False, block_size=16, enable_prefix_caching=True, disable_sliding_window=False, use_v2_block_manager=True, num_lookahead_slots=0, seed=0, swap_space=4, cpu_offload_gb=0, gpu_memory_utilization=0.9, num_gpu_blocks_override=None, max_num_batched_tokens=8192, max_num_seqs=2, max_logprobs=20, disable_log_stats=False, quantization=None, rope_scaling=None, rope_theta=None, enforce_eager=True, max_context_len_to_capture=None, max_seq_len_to_capture=8192, disable_custom_all_reduce=False, tokenizer_pool_size=0, tokenizer_pool_type='ray', tokenizer_pool_extra_config=None, limit_mm_per_prompt=None, mm_processor_kwargs=None, enable_lora=False, max_loras=1, max_lora_rank=16, lora_extra_vocab_size=256, lora_dtype='auto', long_lora_scaling_factors=None, max_cpu_loras=None, fully_sharded_loras=False, enable_prompt_adapter=False, max_prompt_adapters=1, max_prompt_adapter_token=0, device='auto', num_scheduler_steps=1, multi_step_stream_outputs=True, scheduler_delay_factor=0.0, enable_chunked_prefill=True, speculative_model=None, speculative_model_quantization=None, num_speculative_tokens=None, speculative_disable_mqa_scorer=False, speculative_draft_tensor_parallel_size=None, speculative_max_model_len=None, speculative_disable_by_batch_size=None, ngram_prompt_lookup_max=None, ngram_prompt_lookup_min=None, spec_decoding_acceptance_method='rejection_sampler', typical_acceptance_sampler_posterior_threshold=None, typical_acceptance_sampler_posterior_alpha=None, disable_logprobs_during_spec_decoding=None, model_loader_extra_config=None, ignore_patterns=[], preemption_mode=None, served_model_name=['llm'], qlora_adapter_name_or_path=None, otlp_traces_endpoint=None, collect_detailed_traces=None, disable_async_output_proc=False, override_neuron_config=None, scheduling_policy='fcfs', disable_log_requests=True, max_log_len=None, disable_fastapi_docs=False)
|
||
INFO 07-14 17:13:52 config.py:1670] Downcasting torch.float32 to torch.float16.
|
||
INFO 07-14 17:14:03 config.py:887] Defaulting to use mp for distributed inference
|
||
INFO 07-14 17:14:03 config.py:1005] Chunked prefill is enabled with max_num_batched_tokens=8192.
|
||
WARNING 07-14 17:14:03 config.py:380] To see benefits of async output processing, enable CUDA graph. Since, enforce-eager is enabled, async output processor cannot be used
|
||
INFO 07-14 17:14:03 llm_engine.py:237] Initializing an LLM engine (v0.6.3) with config: model='/root/public-storage/models/Qwen/Qwen3.6-35B-A3B', speculative_config=None, tokenizer='/root/public-storage/models/Qwen/Qwen3.6-35B-A3B', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, override_neuron_config=None, rope_scaling=None, rope_theta=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.float16, max_seq_len=100000, download_dir=None, load_format=LoadFormat.AUTO, tensor_parallel_size=4, pipeline_parallel_size=1, disable_custom_all_reduce=False, quantization=None, enforce_eager=True, kv_cache_dtype=auto, quantization_param_path=None, device_config=cuda, decoding_config=DecodingConfig(guided_decoding_backend='outlines'), observability_config=ObservabilityConfig(otlp_traces_endpoint=None, collect_model_forward_time=False, collect_model_execute_time=False), seed=0, served_model_name=llm, use_v2_block_manager=True, num_scheduler_steps=1, chunked_prefill_enabled=True multi_step_stream_outputs=True, enable_prefix_caching=True, use_async_output_proc=False, use_cached_outputs=False, mm_processor_kwargs=None)
|
||
WARNING 07-14 17:14:04 multiproc_gpu_executor.py:53] Reducing Torch parallelism from 64 threads to 1 to avoid unnecessary CPU contention. Set OMP_NUM_THREADS in the external environment to tune this value as needed.
|
||
INFO 07-14 17:14:04 custom_cache_manager.py:17] Setting Triton cache manager to: vllm.triton_utils.custom_cache_manager:CustomCacheManager
|
||
INFO 07-14 17:14:04 selector.py:266] Cannot use FlashAttention-2 backend because the vllm.vllm_flash_attn package is not found. Make sure that vllm_flash_attn was built and installed (on by default).
|
||
INFO 07-14 17:14:04 selector.py:115] Using XFormers backend.
|
||
/usr/local/corex/lib/python3/dist-packages/torch/cuda/__init__.py:51: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
|
||
import pynvml # type: ignore[import]
|
||
/usr/local/corex/lib/python3/dist-packages/torch/cuda/__init__.py:51: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
|
||
import pynvml # type: ignore[import]
|
||
/usr/local/corex/lib/python3/dist-packages/torch/cuda/__init__.py:51: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
|
||
import pynvml # type: ignore[import]
|
||
INFO 07-14 17:14:06 importing.py:10] Triton not installed; certain GPU-related functions will not be available.
|
||
INFO 07-14 17:14:06 importing.py:10] Triton not installed; certain GPU-related functions will not be available.
|
||
INFO 07-14 17:14:06 importing.py:10] Triton not installed; certain GPU-related functions will not be available.
|
||
WARNING:tensorflow:Deprecation warnings have been disabled. Set TF_ENABLE_DEPRECATION_WARNINGS=1 to re-enable them.
|
||
WARNING:tensorflow:Deprecation warnings have been disabled. Set TF_ENABLE_DEPRECATION_WARNINGS=1 to re-enable them.
|
||
WARNING:tensorflow:Deprecation warnings have been disabled. Set TF_ENABLE_DEPRECATION_WARNINGS=1 to re-enable them.
|
||
[1;36m(VllmWorkerProcess pid=22420)[0;0m INFO 07-14 17:14:13 selector.py:266] Cannot use FlashAttention-2 backend because the vllm.vllm_flash_attn package is not found. Make sure that vllm_flash_attn was built and installed (on by default).
|
||
[1;36m(VllmWorkerProcess pid=22420)[0;0m INFO 07-14 17:14:13 selector.py:115] Using XFormers backend.
|
||
[1;36m(VllmWorkerProcess pid=22420)[0;0m INFO 07-14 17:14:13 multiproc_worker_utils.py:216] Worker ready; awaiting tasks
|
||
[1;36m(VllmWorkerProcess pid=22419)[0;0m INFO 07-14 17:14:13 selector.py:266] Cannot use FlashAttention-2 backend because the vllm.vllm_flash_attn package is not found. Make sure that vllm_flash_attn was built and installed (on by default).
|
||
[1;36m(VllmWorkerProcess pid=22419)[0;0m INFO 07-14 17:14:13 selector.py:115] Using XFormers backend.
|
||
[1;36m(VllmWorkerProcess pid=22419)[0;0m INFO 07-14 17:14:13 multiproc_worker_utils.py:216] Worker ready; awaiting tasks
|
||
[1;36m(VllmWorkerProcess pid=22421)[0;0m INFO 07-14 17:14:14 selector.py:266] Cannot use FlashAttention-2 backend because the vllm.vllm_flash_attn package is not found. Make sure that vllm_flash_attn was built and installed (on by default).
|
||
[1;36m(VllmWorkerProcess pid=22421)[0;0m INFO 07-14 17:14:14 selector.py:115] Using XFormers backend.
|
||
[1;36m(VllmWorkerProcess pid=22421)[0;0m INFO 07-14 17:14:14 multiproc_worker_utils.py:216] Worker ready; awaiting tasks
|
||
INFO 07-14 17:14:14 shm_broadcast.py:242] vLLM message queue communication handle: Handle(connect_ip='127.0.0.1', local_reader_ranks=[1, 2, 3], buffer=<vllm.distributed.device_communicators.shm_broadcast.ShmRingBuffer object at 0x7f8887d0e0e0>, local_subscribe_port=56475, remote_subscribe_port=None)
|
||
INFO 07-14 17:14:14 model_runner.py:1112] Starting to load model /root/public-storage/models/Qwen/Qwen3.6-35B-A3B...
|
||
[1;36m(VllmWorkerProcess pid=22419)[0;0m INFO 07-14 17:14:14 model_runner.py:1112] Starting to load model /root/public-storage/models/Qwen/Qwen3.6-35B-A3B...
|
||
[1;36m(VllmWorkerProcess pid=22420)[0;0m INFO 07-14 17:14:14 model_runner.py:1112] Starting to load model /root/public-storage/models/Qwen/Qwen3.6-35B-A3B...
|
||
[1;36m(VllmWorkerProcess pid=22421)[0;0m INFO 07-14 17:14:14 model_runner.py:1112] Starting to load model /root/public-storage/models/Qwen/Qwen3.6-35B-A3B...
|
||
INFO 07-14 17:14:14 selector.py:266] Cannot use FlashAttention-2 backend because the vllm.vllm_flash_attn package is not found. Make sure that vllm_flash_attn was built and installed (on by default).
|
||
INFO 07-14 17:14:14 selector.py:115] Using XFormers backend.
|
||
[1;36m(VllmWorkerProcess pid=22421)[0;0m INFO 07-14 17:14:14 selector.py:266] Cannot use FlashAttention-2 backend because the vllm.vllm_flash_attn package is not found. Make sure that vllm_flash_attn was built and installed (on by default).
|
||
[1;36m(VllmWorkerProcess pid=22421)[0;0m INFO 07-14 17:14:14 selector.py:115] Using XFormers backend.
|
||
[1;36m(VllmWorkerProcess pid=22419)[0;0m INFO 07-14 17:14:14 selector.py:266] Cannot use FlashAttention-2 backend because the vllm.vllm_flash_attn package is not found. Make sure that vllm_flash_attn was built and installed (on by default).
|
||
[1;36m(VllmWorkerProcess pid=22419)[0;0m INFO 07-14 17:14:14 selector.py:115] Using XFormers backend.
|
||
[1;36m(VllmWorkerProcess pid=22420)[0;0m INFO 07-14 17:14:14 selector.py:266] Cannot use FlashAttention-2 backend because the vllm.vllm_flash_attn package is not found. Make sure that vllm_flash_attn was built and installed (on by default).
|
||
[1;36m(VllmWorkerProcess pid=22420)[0;0m INFO 07-14 17:14:14 selector.py:115] Using XFormers backend.
|
||
|
||
Loading safetensors checkpoint shards: 0% Completed | 0/26 [00:00<?, ?it/s]
|
||
|
||
Loading safetensors checkpoint shards: 4% Completed | 1/26 [00:01<00:44, 1.77s/it]
|
||
|
||
Loading safetensors checkpoint shards: 8% Completed | 2/26 [00:02<00:22, 1.08it/s]
|
||
|
||
Loading safetensors checkpoint shards: 12% Completed | 3/26 [00:03<00:29, 1.29s/it]
|
||
|
||
Loading safetensors checkpoint shards: 15% Completed | 4/26 [00:05<00:31, 1.42s/it]
|
||
|
||
Loading safetensors checkpoint shards: 19% Completed | 5/26 [00:06<00:26, 1.24s/it]
|
||
|
||
Loading safetensors checkpoint shards: 23% Completed | 6/26 [00:08<00:28, 1.44s/it]
|
||
|
||
Loading safetensors checkpoint shards: 27% Completed | 7/26 [00:08<00:21, 1.11s/it]
|
||
|
||
Loading safetensors checkpoint shards: 31% Completed | 8/26 [00:10<00:22, 1.26s/it]
|
||
|
||
Loading safetensors checkpoint shards: 35% Completed | 9/26 [00:11<00:20, 1.19s/it]
|
||
|
||
Loading safetensors checkpoint shards: 38% Completed | 10/26 [00:13<00:22, 1.41s/it]
|
||
|
||
Loading safetensors checkpoint shards: 42% Completed | 11/26 [00:13<00:16, 1.07s/it]
|
||
|
||
Loading safetensors checkpoint shards: 46% Completed | 12/26 [00:15<00:17, 1.27s/it]
|
||
|
||
Loading safetensors checkpoint shards: 50% Completed | 13/26 [00:16<00:18, 1.42s/it]
|
||
|
||
Loading safetensors checkpoint shards: 54% Completed | 14/26 [00:18<00:19, 1.59s/it]
|
||
|
||
Loading safetensors checkpoint shards: 58% Completed | 15/26 [00:19<00:14, 1.34s/it]
|
||
|
||
Loading safetensors checkpoint shards: 62% Completed | 16/26 [00:21<00:16, 1.60s/it]
|
||
|
||
Loading safetensors checkpoint shards: 65% Completed | 17/26 [00:22<00:11, 1.25s/it]
|
||
|
||
Loading safetensors checkpoint shards: 69% Completed | 18/26 [00:24<00:11, 1.43s/it]
|
||
|
||
Loading safetensors checkpoint shards: 73% Completed | 19/26 [00:25<00:10, 1.46s/it]
|
||
|
||
Loading safetensors checkpoint shards: 77% Completed | 20/26 [00:27<00:10, 1.71s/it]
|
||
|
||
Loading safetensors checkpoint shards: 81% Completed | 21/26 [00:29<00:07, 1.54s/it]
|
||
|
||
Loading safetensors checkpoint shards: 85% Completed | 22/26 [00:29<00:05, 1.29s/it]
|
||
|
||
Loading safetensors checkpoint shards: 88% Completed | 23/26 [00:32<00:04, 1.64s/it]
|
||
|
||
Loading safetensors checkpoint shards: 92% Completed | 24/26 [00:34<00:03, 1.71s/it]
|
||
|
||
Loading safetensors checkpoint shards: 96% Completed | 25/26 [00:35<00:01, 1.71s/it]
|
||
|
||
Loading safetensors checkpoint shards: 100% Completed | 26/26 [00:36<00:00, 1.39s/it]
|
||
|
||
Loading safetensors checkpoint shards: 100% Completed | 26/26 [00:36<00:00, 1.40s/it]
|
||
|
||
[1;36m(VllmWorkerProcess pid=22420)[0;0m INFO 07-14 17:14:51 model_runner.py:1123] Loading model weights took 16.2303 GB
|
||
INFO 07-14 17:14:51 model_runner.py:1123] Loading model weights took 16.2303 GB
|
||
[1;36m(VllmWorkerProcess pid=22419)[0;0m INFO 07-14 17:14:52 model_runner.py:1123] Loading model weights took 16.2303 GB
|
||
[1;36m(VllmWorkerProcess pid=22421)[0;0m INFO 07-14 17:14:54 model_runner.py:1123] Loading model weights took 16.2303 GB
|
||
INFO 07-14 17:15:03 distributed_gpu_executor.py:57] # GPU blocks: 18502, # CPU blocks: 6553
|
||
INFO 07-14 17:15:03 distributed_gpu_executor.py:61] Maximum concurrency for 100000 tokens per request: 2.96x
|
||
INFO 07-14 17:15:07 serving_chat.py:79] "auto" tool choice has been enabled please note that while the parallel_tool_calls client option is preset for compatibility reasons, it will be ignored.
|
||
INFO 07-14 17:15:07 serving_chat.py:101] Reasoning parser 'qwen3' enabled.
|
||
WARNING 07-14 17:15:07 serving_embedding.py:199] embedding_mode is False. Embedding API will not work.
|
||
INFO 07-14 17:15:07 launcher.py:19] Available routes are:
|
||
INFO 07-14 17:15:07 launcher.py:27] Route: /openapi.json, Methods: HEAD, GET
|
||
INFO 07-14 17:15:07 launcher.py:27] Route: /docs, Methods: HEAD, GET
|
||
INFO 07-14 17:15:07 launcher.py:27] Route: /docs/oauth2-redirect, Methods: HEAD, GET
|
||
INFO 07-14 17:15:07 launcher.py:27] Route: /redoc, Methods: HEAD, GET
|
||
INFO 07-14 17:15:07 launcher.py:27] Route: /health, Methods: GET
|
||
INFO 07-14 17:15:07 launcher.py:27] Route: /tokenize, Methods: POST
|
||
INFO 07-14 17:15:07 launcher.py:27] Route: /detokenize, Methods: POST
|
||
INFO 07-14 17:15:07 launcher.py:27] Route: /v1/models, Methods: GET
|
||
INFO 07-14 17:15:07 launcher.py:27] Route: /version, Methods: GET
|
||
INFO 07-14 17:15:07 launcher.py:27] Route: /v1/chat/completions, Methods: POST
|
||
INFO 07-14 17:15:07 launcher.py:27] Route: /v1/completions, Methods: POST
|
||
INFO 07-14 17:15:07 launcher.py:27] Route: /v1/embeddings, Methods: POST
|
||
INFO: Started server process [22074]
|
||
INFO: Waiting for application startup.
|
||
INFO: Application startup complete.
|
||
INFO: Uvicorn running on socket ('0.0.0.0', 1111) (Press CTRL+C to quit)
|
||
INFO: 127.0.0.1:55232 - "GET /health HTTP/1.1" 200 OK
|
||
INFO: 127.0.0.1:55234 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
||
/usr/local/lib/python3.10/site-packages/pyairports/airports.py:1: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
|
||
from pkg_resources import resource_string
|
||
INFO 07-14 17:15:16 metrics.py:345] Avg prompt throughput: 4.1 tokens/s, Avg generation throughput: 0.1 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.0%, CPU KV cache usage: 0.0%.
|
||
INFO 07-14 17:15:16 metrics.py:361] Prefix cache hit rate: GPU: 0.00%, CPU: 0.00%
|
||
INFO: 127.0.0.1:45424 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
||
INFO: 127.0.0.1:45430 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
||
INFO 07-14 17:15:22 metrics.py:345] Avg prompt throughput: 14.8 tokens/s, Avg generation throughput: 6.3 tokens/s, Running: 2 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.0%, CPU KV cache usage: 0.0%.
|
||
INFO 07-14 17:15:22 metrics.py:361] Prefix cache hit rate: GPU: 66.67%, CPU: 0.00%
|
||
INFO 07-14 17:15:27 metrics.py:345] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 14.2 tokens/s, Running: 2 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.0%, CPU KV cache usage: 0.0%.
|
||
INFO 07-14 17:15:27 metrics.py:361] Prefix cache hit rate: GPU: 66.67%, CPU: 0.00%
|
||
INFO 07-14 17:15:32 metrics.py:345] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 13.1 tokens/s, Running: 2 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.1%, CPU KV cache usage: 0.0%.
|
||
INFO 07-14 17:15:32 metrics.py:361] Prefix cache hit rate: GPU: 66.67%, CPU: 0.00%
|
||
INFO 07-14 17:15:37 metrics.py:345] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 13.7 tokens/s, Running: 2 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.1%, CPU KV cache usage: 0.0%.
|
||
INFO 07-14 17:15:37 metrics.py:361] Prefix cache hit rate: GPU: 66.67%, CPU: 0.00%
|
||
INFO: 127.0.0.1:40456 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
||
INFO: 127.0.0.1:40464 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
||
INFO 07-14 17:15:42 metrics.py:345] Avg prompt throughput: 15.2 tokens/s, Avg generation throughput: 10.5 tokens/s, Running: 2 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.0%, CPU KV cache usage: 0.0%.
|
||
INFO 07-14 17:15:42 metrics.py:361] Prefix cache hit rate: GPU: 80.00%, CPU: 0.00%
|
||
INFO 07-14 17:15:47 metrics.py:345] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 14.1 tokens/s, Running: 2 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.0%, CPU KV cache usage: 0.0%.
|
||
INFO 07-14 17:15:47 metrics.py:361] Prefix cache hit rate: GPU: 80.00%, CPU: 0.00%
|
||
INFO 07-14 17:15:52 metrics.py:345] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 13.4 tokens/s, Running: 2 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.0%, CPU KV cache usage: 0.0%.
|
||
INFO 07-14 17:15:52 metrics.py:361] Prefix cache hit rate: GPU: 80.00%, CPU: 0.00%
|
||
INFO 07-14 17:15:57 metrics.py:345] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 14.0 tokens/s, Running: 2 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.1%, CPU KV cache usage: 0.0%.
|
||
INFO 07-14 17:15:57 metrics.py:361] Prefix cache hit rate: GPU: 80.00%, CPU: 0.00%
|
||
INFO 07-14 17:16:00 launcher.py:57] Shutting down FastAPI HTTP server.
|
||
INFO: Shutting down
|
||
INFO: Waiting for application shutdown.
|
||
INFO: Application shutdown complete.
|
||
INFO 07-14 17:16:00 async_llm_engine.py:63] Engine is gracefully shutting down.
|
||
INFO 07-14 17:16:00 multiproc_worker_utils.py:134] Terminating local vLLM worker processes
|
||
[1;36m(VllmWorkerProcess pid=22419)[0;0m INFO 07-14 17:16:00 multiproc_worker_utils.py:242] Worker exiting
|
||
[1;36m(VllmWorkerProcess pid=22420)[0;0m INFO 07-14 17:16:00 multiproc_worker_utils.py:242] Worker exiting
|
||
[1;36m(VllmWorkerProcess pid=22421)[0;0m INFO 07-14 17:16:00 multiproc_worker_utils.py:242] Worker exiting
|
||
/usr/local/lib/python3.10/multiprocessing/resource_tracker.py:224: UserWarning: resource_tracker: There appear to be 1 leaked shared_memory objects to clean up at shutdown
|
||
warnings.warn('resource_tracker: There appear to be %d '
|