nick/comfyui-serverless
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Target only H200 (sm_90) for SageAttention build
All checks were successful
Build and Push Docker Image / build (push) Successful in 25m31s
Details

Browse Source 
Blackwell (sm_100) may not be fully supported yet.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Nick
2025-12-26 22:12:59 +13:00
parent fef4b8d7ee
commit 929059f812
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
Dockerfile
View File

@@ -65,8 +65,9 @@ WORKDIR /tmp
ENV EXT_PARALLEL=2 ENV EXT_PARALLEL=2
ENV NVCC_APPEND_FLAGS="--threads 2" ENV NVCC_APPEND_FLAGS="--threads 2"
ENV MAX_JOBS=4 ENV MAX_JOBS=4
# Target RunPod GPU architectures: H100/H200(9.0), RTX 5090/Blackwell(10.0) # Target RunPod GPU architectures: H100/H200(9.0)
ENV TORCH_CUDA_ARCH_LIST="9.0;10.0" # Note: Blackwell (10.0) not yet supported by SageAttention
ENV TORCH_CUDA_ARCH_LIST="9.0"
RUN git clone https://github.com/thu-ml/SageAttention.git && \ RUN git clone https://github.com/thu-ml/SageAttention.git && \
cd SageAttention && \ cd SageAttention && \
pip install --no-build-isolation . && \ pip install --no-build-isolation . && \