67a5639c3c
Based on a3c45d3b (last known working docker build):
- yaml: max-num-seqs=2 (fixes t2_n_2), TOPK_SOFTMAX=1 (use prebuilt .so)
- yaml: keep max-model-len=131072, gpu-mem=0.90 (prevents OOM)
- yaml: NO LD_PRELOAD (libcccl not built during docker build)
- xformers: revert to Q-tiling only (flash_attn caused OOM at profiling)
- .dockerignore: exclude all non-essential files from context
- remove libcccl_allocator.so from git tracking
What stays from recent work:
- 14 prebuilt .so (including corex_gdn_chunk_recurrent)
- qwen3_5.py with .float() fix and chunk_recurrent support
- All vendor_overrides and CCCL preload source (for future use)
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
|
|
- '2'
|
|
- --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'
|