Files
project_6/computility-run.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
- '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'
# --- MoE kernel selection ---
- name: BI100_MOE_COREX_DIRECT_ROUTED
value: '1'
- name: BI100_MOE_COREX_TOPK_SOFTMAX
value: '1'
# --- GDN kernel selection ---
- name: BI100_GDN_COREX_PACKED_DECODE
value: '1'
# --- Hybrid KV/GDN cache ---
- name: BI100_HYBRID_KV_ACCOUNTING
value: full_attention
- name: BI100_GDN_CACHE_POLICY
value: admission64
- name: BI100_GDN_RESTORE_MODE
value: hybrid64