[CI/Build] Replace vllm.entrypoints.openai.api_server entrypoint with vllm serve command (#25967)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

docker/Dockerfile

@@ -565,5 +565,5 @@ ENTRYPOINT ["./sagemaker-entrypoint.sh"]
 
 FROM vllm-openai-base AS vllm-openai
 
-ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]
+ENTRYPOINT ["vllm", "serve"]
 #################### OPENAI API SERVER ####################

docker/Dockerfile.cpu

@@ -177,4 +177,4 @@ RUN --mount=type=cache,target=/root/.cache/uv \
     --mount=type=bind,from=vllm-build,src=/workspace/vllm/dist,target=dist \
     uv pip install dist/*.whl
 
-ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]
+ENTRYPOINT ["vllm", "serve"]

docker/Dockerfile.ppc64le

@@ -314,4 +314,4 @@ WORKDIR /workspace/
 
 RUN ln -s /workspace/vllm/tests && ln -s /workspace/vllm/examples && ln -s /workspace/vllm/benchmarks
 
-ENTRYPOINT ["python", "-m", "vllm.entrypoints.openai.api_server"]
+ENTRYPOINT ["vllm", "serve"]

docker/Dockerfile.s390x

@@ -309,4 +309,4 @@ USER 2000
 WORKDIR /home/vllm
 
 # Set the default entrypoint
-ENTRYPOINT ["python", "-m", "vllm.entrypoints.openai.api_server"]
+ENTRYPOINT ["vllm", "serve"]

docker/Dockerfile.xpu

@@ -69,4 +69,4 @@ RUN --mount=type=cache,target=/root/.cache/pip \
 
 # install development dependencies (for testing)
 RUN python3 -m pip install -e tests/vllm_test_utils
-ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]
+ENTRYPOINT ["vllm", "serve"]