| FROM vllm/vllm-openai:latest | |
| COPY model /model | |
| ENV MODEL=/model | |
| EXPOSE 8000 | |
| ENTRYPOINT ["vllm", "serve", "/model", "--host", "0.0.0.0", "--port", "8000", "--dtype", "bfloat16", "--max-model-len", "4096", "--tensor-parallel-size", "1"] | |
| FROM vllm/vllm-openai:latest | |
| COPY model /model | |
| ENV MODEL=/model | |
| EXPOSE 8000 | |
| ENTRYPOINT ["vllm", "serve", "/model", "--host", "0.0.0.0", "--port", "8000", "--dtype", "bfloat16", "--max-model-len", "4096", "--tensor-parallel-size", "1"] | |