diff --git a/docker/Dockerfile b/docker/Dockerfile index d7823f3211..ef166665c5 100644 --- a/docker/Dockerfile +++ b/docker/Dockerfile @@ -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).