owen/worker-vllm
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #318 from runpod-workers/feat/0.24.0

Browse Source 
feat: update to 0.24.0
This commit is contained in:
Dean Quiñanola
2026-07-24 11:30:29 -07:00
committed by GitHub
parent e786204cf5 86b7951c39
commit 51e1aee770
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Dockerfile
+1 -1
View File
@@ -18,7 +18,7 @@ RUN ldconfig /usr/local/cuda-13.0/compat/
# Install vLLM with FlashInfer - use CUDA 130 PyTorch wheels # Install vLLM with FlashInfer - use CUDA 130 PyTorch wheels
RUN --mount=type=cache,target=/root/.cache/uv \ RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install --system "packaging>=24.2" && \ uv pip install --system "packaging>=24.2" && \
uv pip install --system "vllm[flashinfer]==0.23.0" && \ uv pip install --system "vllm[flashinfer]==0.24.0" && \
uv pip install --system git+https://github.com/deepseek-ai/DeepGEMM.git@714dd1a4a980f7937a74343d19a8eba4fe321480 --no-build-isolation && \ uv pip install --system git+https://github.com/deepseek-ai/DeepGEMM.git@714dd1a4a980f7937a74343d19a8eba4fe321480 --no-build-isolation && \
uv pip install --system --force-reinstall --no-deps nixl-cu13 uv pip install --system --force-reinstall --no-deps nixl-cu13