[Docker] Remove redundant flashinfer download-cubin step (#46517)
Signed-off-by: mgoin <mgoin64@gmail.com> Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
@@ -898,13 +898,6 @@ RUN --mount=type=cache,target=/opt/uv/cache \
|
||||
fi; \
|
||||
fi
|
||||
|
||||
# Download FlashInfer precompiled cubins AFTER all pip installs are done.
|
||||
# This must run after the vLLM wheel and EP kernels installs above, because
|
||||
# those can reinstall/touch flashinfer packages. Downloading cubins earlier
|
||||
# (in the flashinfer-jit-cache layer) causes ~2.5 GB of layer duplication
|
||||
# when a later pip install overwrites flashinfer package files.
|
||||
RUN flashinfer show-config && flashinfer download-cubin
|
||||
|
||||
# CUDA image changed from /usr/local/nvidia to /usr/local/cuda in 12.8 but will
|
||||
# return to /usr/local/nvidia in 13.0 to allow container providers to mount drivers
|
||||
# consistently from the host (see https://github.com/vllm-project/vllm/issues/18859).
|
||||
|
||||
Reference in New Issue
Block a user