f8e8b6fb28
1. Dockerfile: 去掉ex_engine COPY和所有CUDA编译RUN步骤 - 只剩1个RUN: patch_ops.sh部署预编译.so和serving层 2. patch_ops.sh: exit 2 → exit 0, 跳过所有CUDA编译 - VLLM_ROOT找不到时不再abort - 去掉build_moe_topk/build_unified_bridge/py_compile 3. computility-run.yaml: 恢复comp168参数 - max_model_len: 80000 → 100000 - gpu_memory_utilization: 0.95 → 0.90 - 去掉 --max-num-batched-tokens --enable-chunked-prefill
47 lines
1.1 KiB
YAML
47 lines
1.1 KiB
YAML
concurrency: 1
|
|
command:
|
|
- python3
|
|
- -m
|
|
- vllm.entrypoints.openai.api_server
|
|
- --model
|
|
- /model
|
|
- --served-model-name
|
|
- llm
|
|
- --max-model-len
|
|
- '100000'
|
|
- --gpu-memory-utilization
|
|
- '0.90'
|
|
- --trust-remote-code
|
|
- -tp
|
|
- '4'
|
|
- --max-num-seqs
|
|
- '2'
|
|
- --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
|
|
- '8192'
|
|
- --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'
|