Files
step3p5-vllm-nv/Dockerfile
zhousha 7a7c4986b9
Some checks failed
Docker Build and Push / docker (push) Failing after 2s
Add NVIDIA vLLM image and ModelHub release workflow
2026-09-29 15:39:44 +08:00

6 lines
275 B
Docker

FROM harbor.4pd.io/hardcore-tech/vllm/vllm-openai:v0.25.0-cu129
# Text inference does not require the incompatible TorchCodec video decoder.
RUN python3 -m pip uninstall -y torchcodec
RUN python3 -c "import vllm.entrypoints.openai.api_server; print('API server import OK')"