update flashinfer

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
This commit is contained in:
tzhouam committed 2026-02-12 08:52:06 +00:00
1 parent 3e89c99001
commit 8c1df5c704
1 file changed
+6
+6
View File
@@ -38,6 +38,12 @@ RUN /bin/bash -c 'uv pip install --python "$(python3 -c "import sys; print(sys.e
# Pin nvidia-cublas-cu12 after vllm-omni install so dependency resolution does not overwrite it
RUN uv pip install --system --upgrade --force-reinstall "nvidia-cublas-cu12==12.9.1.4"
RUN /bin/bash -c 'FLASHINFER_CUDA_TAG="$(python3 -c "import torch; print((torch.version.cuda or \"12.4\").replace(\".\", \"\"))")" && \
uv pip install --system --upgrade --force-reinstall \
"flashinfer-python==0.6.3" \
"flashinfer-cubin==0.6.3" \
"flashinfer-jit-cache==0.6.3" \
--extra-index-url "https://flashinfer.ai/whl/cu${FLASHINFER_CUDA_TAG}"'
RUN ln -sf /usr/bin/python3 /usr/bin/python