38eca5c26a
Root cause of 10 consecutive OOM failures: - 'return zeros during profiling' hack → vllm overestimates free memory → allocates 7942 blocks → first real request OOMs - blocks cap 5000 → band-aid that masks profiling bug - gpu-memory-utilization 0.80 → unnecessary reduction from working 0.90 - max-num-seqs 2 → doubles peak activation memory - PYTORCH_CUDA_ALLOC_CONF max_split_size_mb:512 → causes fragmentation Restoringa3c45d3bparameters that actually work: - yaml: max-model-len=131072, gpu-mem=0.90, max-num-seqs=1, batched-tokens=8192 - patch_xformers_sdpa_seq.py: Q-tiling (real memory optimization, not zeros hack) - patch_block_major_worker_capacity.py: no blocks cap, just reserve_block_major - patch_ops.sh: remove all docker-build-time compilation (all .so are prebuilt) Only change froma3c45d3b: BI100_MOE_COREX_TOPK_SOFTMAX=1 (enable corex topk) Kept fixes: - protocol.py extra=allow (recover 180 rejected replay requests) - corex_gdn_chunk_recurrent.so pybind kwargs (prebuilt with fixed signature)
50 lines
1.1 KiB
YAML
50 lines
1.1 KiB
YAML
concurrency: 1
|
|
command:
|
|
- python3
|
|
- -m
|
|
- vllm.entrypoints.openai.api_server
|
|
- --model
|
|
- /model
|
|
- --served-model-name
|
|
- llm
|
|
- --max-model-len
|
|
- '131072'
|
|
- --gpu-memory-utilization
|
|
- '0.90'
|
|
- --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
|
|
- --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'
|