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

Reduce CUDA compilation parallelism for 16GB RAM
Some checks failed
Build and Push Docker Image / build (push) Failing after 15m53s
Details

Browse Source 
🤖 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 16:58:39 +13:00
parent 7a8b59f471
commit fef4b8d7ee
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
Dockerfile
View File

@@ -62,9 +62,9 @@ RUN pip install -r /tmp/requirements.txt && rm -rf /root/.cache/pip
# Compile SageAttention 2.2 from source with no build isolation # Compile SageAttention 2.2 from source with no build isolation
WORKDIR /tmp WORKDIR /tmp
ENV EXT_PARALLEL=4 ENV EXT_PARALLEL=2
ENV NVCC_APPEND_FLAGS="--threads 8" ENV NVCC_APPEND_FLAGS="--threads 2"
ENV MAX_JOBS=32 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), RTX 5090/Blackwell(10.0)
ENV TORCH_CUDA_ARCH_LIST="9.0;10.0" ENV TORCH_CUDA_ARCH_LIST="9.0;10.0"
RUN git clone https://github.com/thu-ml/SageAttention.git && \ RUN git clone https://github.com/thu-ml/SageAttention.git && \