8030a11b96
project_7 docker build 已在竞赛平台验证成功。 完整搬运 wudixzy/competition stack: - qwen3_5.py 2615 行 (12 个 corex .so 调用) - patch_ops.sh 251 行 (set -eo pipefail + cd dirname) - 12 prebuilt corex .so (SHA256 verified) - 13 CUDA .cu 源码 + 11 build scripts - 9 vendor overrides (block/sampler/scheduler) - transformers-4.55.3 offline wheel - computility-run.yaml: 262144 max-model-len, BI100 env vars - Dockerfile 结构不变 (COPY qwen3_6_scripts + RUN patch_ops.sh)
45 lines
1005 B
YAML
45 lines
1005 B
YAML
concurrency: 1
|
|
command:
|
|
- python3
|
|
- -m
|
|
- vllm.entrypoints.openai.api_server
|
|
- --model
|
|
- /model
|
|
- --served-model-name
|
|
- llm
|
|
- --max-model-len
|
|
- '262144'
|
|
- --gpu-memory-utilization
|
|
- '0.9'
|
|
- --trust-remote-code
|
|
- -tp
|
|
- '4'
|
|
- --max-num-seqs
|
|
- '1'
|
|
- --disable-log-requests
|
|
- --disable-frontend-multiprocessing
|
|
- --max-num-batched-tokens
|
|
- '8192'
|
|
- --enable-chunked-prefill
|
|
- --max-seq-len-to-capture
|
|
- '32768'
|
|
- --enable-auto-tool-choice
|
|
- --tool-call-parser
|
|
- qwen3_coder
|
|
- --reasoning-parser
|
|
- qwen3
|
|
- --enable-prefix-caching
|
|
env:
|
|
- name: VLLM_ENGINE_ITERATION_TIMEOUT_S
|
|
value: 3600
|
|
- name: BI100_MOE_COREX_DIRECT_ROUTED
|
|
value: 1
|
|
- name: BI100_GDN_COREX_PACKED_DECODE
|
|
value: 1
|
|
- name: BI100_HYBRID_KV_ACCOUNTING
|
|
value: full_attention
|
|
- name: BI100_GDN_CACHE_POLICY
|
|
value: admission64
|
|
- name: BI100_GDN_RESTORE_MODE
|
|
value: hybrid64
|