Enable CodeGen vLLM (#1636)

Signed-off-by: Wang, Xigui <xigui.wang@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
xiguiw
2025-03-13 10:38:47 +08:00
committed by GitHub
parent adcd113f53
commit effa2a28cf
8 changed files with 421 additions and 196 deletions

View File

@@ -6,9 +6,21 @@ pushd "../../" > /dev/null
source .set_env.sh
popd > /dev/null
export host_ip=$(hostname -I | awk '{print $1}')
if [ -z "${HUGGINGFACEHUB_API_TOKEN}" ]; then
echo "Error: HUGGINGFACEHUB_API_TOKEN is not set. Please set HUGGINGFACEHUB_API_TOKEN"
fi
if [ -z "${host_ip}" ]; then
echo "Error: host_ip is not set. Please set host_ip first."
fi
export no_proxy=${no_proxy},${host_ip}
export LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"
export TGI_LLM_ENDPOINT="http://${host_ip}:8028"
export LLM_ENDPOINT="http://${host_ip}:8028"
export MEGA_SERVICE_HOST_IP=${host_ip}
export LLM_SERVICE_HOST_IP=${host_ip}
export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:7778/v1/codegen"
export MODEL_CACHE="./data"