qwen_deploy/docker/start.sh
2024-04-06 10:29:10 +08:00

1 line
192 B
Bash

python -m vllm.entrypoints.openai.api_server --dtype bfloat16 --model ${MODEL_PATH} --max-model-len ${MAX_MODEL_LEN} --host ${HOST} --port ${PORT} --api-key ${API_KEY} --root-path ${ROOT_PATH}