From vllm/vllm-openai:v0.8.4

RUN git clone https://github.com/vllm-project/vllm.git && cd vllm && git fetch origin pull/16618/head:pr-16618 && VLLM_USE_PRECOMPILED=1 pip install --editable .

EXPOSE 8080

# Set the serve script as the entrypoint
ENTRYPOINT ["/usr/bin/serve"]
