Skip to content

[CI] Update FlashInfer to 0.2.6.post1 #19297

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Jun 11, 2025
Merged

[CI] Update FlashInfer to 0.2.6.post1 #19297

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
cb2d8e7
Update FlashInfer to 0.2.6
mgoin Jun 6, 2025
572b3a2
Update Dockerfile
mgoin Jun 8, 2025
58546f6
Build AOT kernels
mgoin Jun 9, 2025
52e83f5
Merge branch 'main' into update-to-flashinfer-0.2.6
mgoin Jun 9, 2025
2ab812f
python3
mgoin Jun 10, 2025
3195f57
Add pre-built wheel
mgoin Jun 10, 2025
7103af2
Merge branch 'main' into update-to-flashinfer-0.2.6
mgoin Jun 10, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 17 additions & 15 deletions docker/Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -243,30 +243,32 @@ RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist
--extra-index-url https://download.pytorch.org/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')

# If we need to build FlashInfer wheel before its release:
# $ export FLASHINFER_ENABLE_AOT=1
# $ # Note we remove 7.0 from the arch list compared to the list below, since FlashInfer only supports sm75+
# $ export TORCH_CUDA_ARCH_LIST='7.5 8.0 8.6 8.9 9.0+PTX'
# $ export TORCH_CUDA_ARCH_LIST='7.5 8.0 8.9 9.0a 10.0a'
# $ git clone https://github.com/flashinfer-ai/flashinfer.git --recursive
# $ cd flashinfer
# $ git checkout 524304395bd1d8cd7d07db083859523fcaa246a4
# $ rm -rf build
# $ python3 setup.py bdist_wheel --dist-dir=dist --verbose
# $ ls dist
# $ # upload the wheel to a public location, e.g. https://wheels.vllm.ai/flashinfer/524304395bd1d8cd7d07db083859523fcaa246a4/flashinfer_python-0.2.1.post1+cu124torch2.5-cp38-abi3-linux_x86_64.whl
# $ git checkout v0.2.6.post1
# $ python -m flashinfer.aot
# $ python -m build --no-isolation --wheel
# $ ls -la dist
# -rw-rw-r-- 1 mgoin mgoin 205M Jun 9 18:03 flashinfer_python-0.2.6.post1-cp39-abi3-linux_x86_64.whl
# $ # upload the wheel to a public location, e.g. https://wheels.vllm.ai/flashinfer/v0.2.6.post1/flashinfer_python-0.2.6.post1-cp39-abi3-linux_x86_64.whl

RUN --mount=type=cache,target=/root/.cache/uv \
. /etc/environment && \
if [ "$TARGETPLATFORM" != "linux/arm64" ]; then \
# FlashInfer alreary has a wheel for PyTorch 2.7.0 and CUDA 12.8. This is enough for CI use
# FlashInfer already has a wheel for PyTorch 2.7.0 and CUDA 12.8. This is enough for CI use
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The comment # FlashInfer already has a wheel for PyTorch 2.7.0 and CUDA 12.8. This is enough for CI use now precedes logic that unconditionally builds FlashInfer v0.2.6 from source (for non-arm64 platforms). This comment seems to refer to the previous state with FlashInfer v0.2.5, where a pre-built wheel was used for CUDA 12.8.

Could we update this comment to more accurately reflect the current strategy of building v0.2.6 from source? This would prevent potential confusion for future readers.

    # Building FlashInfer v0.2.6 from source as pre-built wheels for this version are not yet available.

if [[ "$CUDA_VERSION" == 12.8* ]]; then \
uv pip install --system https://download.pytorch.org/whl/cu128/flashinfer/flashinfer_python-0.2.5%2Bcu128torch2.7-cp38-abi3-linux_x86_64.whl; \
uv pip install --system https://download.pytorch.org/whl/cu128/flashinfer/flashinfer_python-0.2.6.post1%2Bcu128torch2.7-cp39-abi3-linux_x86_64.whl; \
else \
export TORCH_CUDA_ARCH_LIST='7.5 8.0 8.9 9.0+PTX'; \
CUDA_MAJOR="${CUDA_VERSION%%.*}"; \
if [ "$CUDA_MAJOR" -lt 12 ]; then \
export FLASHINFER_ENABLE_SM90=0; \
fi; \
uv pip install --system --no-build-isolation "git+https://github.com/flashinfer-ai/flashinfer@21ea1d2545f74782b91eb8c08fd503ac4c0743fc" ; \
export TORCH_CUDA_ARCH_LIST='7.5 8.0 8.9 9.0a 10.0a' && \
git clone https://github.com/flashinfer-ai/flashinfer.git --single-branch --branch v0.2.6.post1 --recursive && \
# Needed to build AOT kernels
(cd flashinfer && \
python3 -m flashinfer.aot && \
uv pip install --system --no-build-isolation . \
) && \
rm -rf flashinfer; \
fi \
fi
COPY examples examples
Expand Down