19 lines
396 B
Bash
19 lines
396 B
Bash
#!/bin/bash
|
|
|
|
# pip3 install vllm
|
|
|
|
model_name_or_path="meta-llama/Llama-2-7b-chat-hf"
|
|
port=8000
|
|
|
|
while getopts "m:p:" flag
|
|
do
|
|
# shellcheck disable=SC2220
|
|
case "${flag}" in
|
|
m) model_name_or_path=${OPTARG};;
|
|
p) port=${OPTARG};;
|
|
esac
|
|
done
|
|
|
|
python -m vllm.entrypoints.openai.api_server --model "${model_name_or_path}" \
|
|
--port "${port}" --enforce-eager
|