Update Dockerfile

Dockerfile

@@ -5,8 +5,8 @@ FROM vllm/vllm-openai:v0.10.0
 # NOTE: Make sure the version of vLLM matches the base image!
 RUN uv pip install --system vllm[audio]==0.10.0
 
-# Export for runtime environment
-CMD vllm serve "meta-llama/Llama-3.2-3B-Instruct" \
+ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]
+CMD "meta-llama/Llama-3.2-3B-Instruct" \
   --task generate \
   --revision "0cb88a4f764b7a12671c53f0838cd831a0843b95" \
   --code-revision "0cb88a4f764b7a12671c53f0838cd831a0843b95" \