vllm_serve.sh 171 Bytes
Newer Older
dengjb's avatar
update  
dengjb committed
1
2
3
4
5
6
vllm serve /path/of/Qwen/Qwen3Guard-Gen-8B/ \
    --trust-remote-code \
    --max-model-len 32768 \
    --served-model-name qwen3-guard \
    --dtype bfloat16 \
    -tp 1