8acc47129b
MoE kernels: - topk_softmax: add .contiguous() + nan_to_num + re-normalize weights - direct_routed: nan_to_num on w2_reduce output - exact_reduce: nan_to_num on serial_float output GDN kernels: - packed_decode: nan_to_num on core_out BI-V100 CUB may produce non-finite values in fp16 softmax/reduce. These guards prevent garbage propagation without disabling the kernels. max-model-len: 256000 → 131072 (4x32GB BI-V100 OOM prevention) Dockerfile: unchanged (no force push needed)
48 lines
1.0 KiB
YAML
48 lines
1.0 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
|
|
- '0.95'
|
|
- --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
|