[Frontend][Build] Add vllm download-kernels for FlashInfer precompiled kernels (#58765)

Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Misha Goin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Misha Goin
2026-10-09 21:22:35 -07:00
committed by GitHub
co-authored by Claude Opus 5.5
parent be0823357f
commit 29e4d2d42e
15 changed files with 309 additions and 20 deletions
+5 -7
View File
@@ -936,13 +936,11 @@ RUN --mount=type=cache,target=/opt/uv/cache \
fi && \
rm /tmp/requirements-cuda.txt /tmp/common.txt
# Install FlashInfer JIT cache (requires CUDA-version-specific index URL)
# https://docs.flashinfer.ai/installation.html
# From versions.json: .flashinfer.version
ARG FLASHINFER_VERSION=0.7.0.post1
RUN --mount=type=cache,target=/opt/uv/cache \
uv pip install --system flashinfer-jit-cache==${FLASHINFER_VERSION} \
--index-url https://flashinfer.ai/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')
# Install FlashInfer's precompiled kernels for all GPU architectures (the default).
# `vllm download-kernels` wraps this command but vLLM is only installed in later
# stages, and running it there would rebuild this large layer for every wheel.
RUN --mount=type=cache,target=/opt/pip/cache \
PIP_CACHE_DIR=/opt/pip/cache flashinfer download-kernels
# ============================================================
# OPENAI API SERVER DEPENDENCIES
-3
View File
@@ -73,9 +73,6 @@
"RUN_WHEEL_CHECK": {
"default": "true"
},
"FLASHINFER_VERSION": {
"default": "0.7.0.post1"
},
"GDRCOPY_CUDA_VERSION": {
"default": "12.8"
},