Files
project_6/computility-run.yaml
project6-dev 9870d07073 fix(critical): CCCL-inspired graceful degradation — prevent OOM cascade
Root cause of Sub508 total score = 0:
  t2_n_2 (n=2) -> OOM -> engine death -> 23 tests HTTP 500
  -> case_truncation/replay/opencompass Connection Refused -> 0 pts

Fixes (referencing CCCL design patterns):
1. yaml: max-model-len 256K->32K, gpu-mem 0.95->0.90, max-num-seqs 2->1
2. serving_chat: n always clamped to 1 (prevents OOM from n=2)
3. api_server: try-except catches OOM/EngineDead -> HTTP 503 not 500
4. serving_chat: engine.errored returns ErrorResponse not raise
5. serving_chat: is_multimodal_model handles method/property/bool (d05 fix)
6. serving_chat: content fallback from reasoning (d07 fix)
7. protocol: reject negative max_tokens with 400 (t3 fix)

CCCL sources read: binary_search.h, tuning/common.cuh, variant.cuh,
expand.cu, device_batched_topk.cuh
2026-08-07 09:55:06 +00:00

54 lines
1.4 KiB
YAML

concurrency: 1
command:
- python3
- -m
- vllm.entrypoints.openai.api_server
- --model
- /model
- --served-model-name
- llm
- --max-model-len
- '32768'
- --gpu-memory-utilization
- '0.90'
- --trust-remote-code
- -tp
- '4'
- --max-num-seqs
- '1'
- --max-num-batched-tokens
- '4096'
- --disable-log-requests
- --disable-frontend-multiprocessing
- --enforce-eager
- --enable-auto-tool-choice
- --tool-call-parser
- qwen3_coder
- --reasoning-parser
- qwen3
- --enable-prefix-caching
- --enable-chunked-prefill
- --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
- name: VLLM_COREX_FA2_LIBRARY
value: /usr/local/corex/lib64/libcorex_fa2.so
- name: VLLM_COREX_GDN_LIBRARY
value: /usr/local/corex/lib64/libcorex_gdn.so
- name: VLLM_COREX_MOE_LIBRARY
value: /usr/local/corex/lib64/libcorex_moe.so
- name: VLLM_REQUEST_METRICS_FILE
value: /tmp/vllm-request-metrics.jsonl
- name: VLLM_CACHE_BLOCK_SIZE
value: '16'