Files
project_6/computility-run.yaml.bak
Claude cf1b701afe fix(build): 回退qwen3_6_scripts+ex_engine到26e6cb40(能得分版本)
唯一改动: computility-run.yaml max_model_len 80000→100000

26e6cb40是Sub520能在竞赛平台docker build成功并得分的版本
之后所有commit都导致docker build失败
根因: 新增的65个文件(vendor_overrides/prebuilt/*.so/wheels等)
可能触发了竞赛平台docker build的某个限制

本次回退:
- qwen3_6_scripts/: 110→45文件(删掉65个新增文件)
- ex_engine/: 恢复到26e6cb40完全一致
- Dockerfile: 恢复5个RUN步骤结构(已验证能build)
- computility-run.yaml: max_model_len=100000(避免replay 400拒绝)
2026-08-12 01:33:24 +00:00

51 lines
1.3 KiB
YAML

concurrency: 1
command:
- python3
- /workspace/qwen3_6_scripts/launch_server.py
- --model
- /model
- --served-model-name
- llm
- --max-model-len
- '80000'
- --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
- --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'
- name: BI100_MOE_COREX_DIRECT_ROUTED
value: '1'
- name: BI100_GDN_COREX_PACKED_DECODE
value: '1'