vllm
serve
/opt/local-models/qwen36-35b-a3b-hf
--served-model-name
Qwen/Qwen3.6-35B-A3B
--enable-auto-tool-choice
--tool-call-parser
hermes
--dtype
half
--host
0.0.0.0
--port
8001
--tensor-parallel-size
4
--max-model-len
131072
--gpu-memory-utilization
0.95
--trust-remote-code
--generation-config
vllm
-O=3
--reasoning-parser
qwen3
--async-scheduling
--language-model-only
