81875fff52
Sub168 log analysis proves: - corex_gdn.py: dlopen /usr/local/corex/lib64/libcorex_gdn.so (decode) - corex_moe.py: ix_moe_bridge → ixformer::infer 7-step fused MoE pipeline - topk_softmax → moe_gen_idx → expand → group_gemm(w13) → silu → group_gemm(w2) → combine - corex_fa2.py: ixformer.functions flash_attn (packed/paged/chunked prefill + paged decode) Previous corex modules were pure PyTorch fakes with matching log messages. Now they actually call the ixformer C++ API via ix_moe_bridge.so. computility-run.yaml aligned to Sub168: max-model-len=256000, max-seq-len-to-capture=32768 Source reference: - upstream_ref/xllm/xllm/core/kernels/ilu/ixformer.h (C++ API declarations) - upstream_ref/xllm/xllm/core/kernels/ilu/fused_moe.cpp (MoE call pattern) - upstream_ref/xllm/xllm/core/layers/npu_torch/qwen3_gated_delta_net_base.cpp (GDN) - dockerrizhi.txt lines 310-397 (Sub168 runtime log)
50 lines
1.2 KiB
YAML
50 lines
1.2 KiB
YAML
concurrency: 1
|
|
command:
|
|
- python3
|
|
- -m
|
|
- vllm.entrypoints.openai.api_server
|
|
- --model
|
|
- /model
|
|
- --served-model-name
|
|
- llm
|
|
- --max-model-len
|
|
- '256000'
|
|
- --gpu-memory-utilization
|
|
- '0.95'
|
|
- --trust-remote-code
|
|
- -tp
|
|
- '4'
|
|
- --max-num-seqs
|
|
- '2'
|
|
- --max-num-batched-tokens
|
|
- '4096'
|
|
- --enable-chunked-prefill
|
|
- --disable-log-requests
|
|
- --disable-frontend-multiprocessing
|
|
- --enforce-eager
|
|
- --enable-auto-tool-choice
|
|
- --tool-call-parser
|
|
- qwen3_coder
|
|
- --reasoning-parser
|
|
- qwen3
|
|
- --enable-prefix-caching
|
|
- --max-seq-len-to-capture
|
|
- '32768'
|
|
- --dtype
|
|
- half
|
|
env:
|
|
- name: VLLM_ENGINE_ITERATION_TIMEOUT_S
|
|
value: '3600'
|
|
- name: VLLM_ATTENTION_BACKEND
|
|
value: XFORMERS
|
|
- name: ENABLE_CUSTOM_IPC
|
|
value: '1'
|
|
- name: PYTHONPATH
|
|
value: /usr/local/corex/lib/python3/dist-packages:/usr/local/corex/lib64/python3/dist-packages
|
|
- name: LD_LIBRARY_PATH
|
|
value: /usr/local/corex/lib64:/usr/local/openmpi/lib:/usr/local/corex/lib64/python3/dist-packages/ixformer
|
|
- name: PYTORCH_CUDA_ALLOC_CONF
|
|
value: max_split_size_mb:512
|
|
- name: OMP_NUM_THREADS
|
|
value: '1'
|