Skip to content

[CI] Add SM120 to the Dockerfile #19794

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 25, 2025
+3 −3
Merged

[CI] Add SM120 to the Dockerfile #19794

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
8e8d3af
Add SM120 to the Dockerfile
mgoin Jun 18, 2025
08acbbf
Update Dockerfile
mgoin Jun 18, 2025
f3bddb6
Update Dockerfile
mgoin Jun 18, 2025
043083a
Merge branch 'main' into add-sm120-dockerfile
mgoin Jun 19, 2025
4d17005
Merge branch 'add-sm120-dockerfile' of https://github.com/neuralmagic…
mgoin Jun 19, 2025
47c4540
Merge branch 'main' into add-sm120-dockerfile
mgoin Jun 20, 2025
2dd24eb
Merge branch 'main' into add-sm120-dockerfile
mgoin Jun 23, 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
6 changes: 3 additions & 3 deletions docker/Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
# can be useful for both `dev` and `test`
# explicitly set the list to avoid issues with torch 2.2
# see https://github.com/pytorch/pytorch/pull/123243
ARG torch_cuda_arch_list='7.0 7.5 8.0 8.9 9.0 10.0+PTX'
ARG torch_cuda_arch_list='7.0 7.5 8.0 8.9 9.0 10.0 12.0'
ENV TORCH_CUDA_ARCH_LIST=${torch_cuda_arch_list}
# Override the arch list for flash-attn to reduce the binary size
ARG vllm_fa_cmake_gpu_arches='80-real;90-real'
Expand Down Expand Up @@ -244,7 +244,7 @@ RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist

# If we need to build FlashInfer wheel before its release:
# $ # 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 8.9 9.0a 10.0a'
# $ export TORCH_CUDA_ARCH_LIST='7.5 8.0 8.9 9.0a 10.0a 12.0'
# $ git clone https://github.com/flashinfer-ai/flashinfer.git --recursive
# $ cd flashinfer
# $ git checkout v0.2.6.post1
Expand All @@ -261,7 +261,7 @@ if [ "$TARGETPLATFORM" != "linux/arm64" ]; then \
if [[ "$CUDA_VERSION" == 12.8* ]]; then \
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 9.0a 10.0a' && \
export TORCH_CUDA_ARCH_LIST='7.5 8.0 8.9 9.0a 10.0a 12.0' && \
git clone https://github.com/flashinfer-ai/flashinfer.git --single-branch --branch v0.2.6.post1 --recursive && \
# Needed to build AOT kernels
(cd flashinfer && \
Expand Down