c6aa1b9c62
Sub655 root cause: OpenAIBaseModel had extra='forbid', rejecting max_completion_tokens and reasoning_effort as 'Extra inputs not permitted'. 180/881 replay requests returned HTTP 400 instead of being processed. Fix: extra='allow'. The fold_max_completion_tokens validator already converts max_completion_tokens→max_tokens correctly. Unknown fields like reasoning_effort are now silently accepted instead of 400'd. Also resolved yaml merge conflict (keep upstream 0.80 gpu-mem, no LD_PRELOAD).
52 lines
1.2 KiB
YAML
52 lines
1.2 KiB
YAML
concurrency: 1
|
|
command:
|
|
- python3
|
|
- -m
|
|
- vllm.entrypoints.openai.api_server
|
|
- --model
|
|
- /model
|
|
- --served-model-name
|
|
- llm
|
|
- --max-model-len
|
|
- '80000'
|
|
- --gpu-memory-utilization
|
|
- '0.80'
|
|
- --trust-remote-code
|
|
- -tp
|
|
- '4'
|
|
- --max-num-seqs
|
|
- '2'
|
|
- --disable-log-requests
|
|
- --disable-frontend-multiprocessing
|
|
- --max-num-batched-tokens
|
|
- '4096'
|
|
- --enable-chunked-prefill
|
|
- --max-seq-len-to-capture
|
|
- '32768'
|
|
- --enable-auto-tool-choice
|
|
- --tool-call-parser
|
|
- qwen3_coder
|
|
- --reasoning-parser
|
|
- qwen3
|
|
- --enable-prefix-caching
|
|
- --enforce-eager
|
|
- --dtype
|
|
- half
|
|
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
|
|
- name: BI100_MOE_COREX_TOPK_SOFTMAX
|
|
value: '1'
|
|
- name: PYTORCH_CUDA_ALLOC_CONF
|
|
value: max_split_size_mb:512
|