Adding CUDA Support for stable-diffusion.cpp#7
Merged
Conversation
Adds ubuntu-latest-cuda and windows-latest-cuda jobs covering sm_75 through sm_120, modeled after the llama.cpp CUDA CI. Linux installs CUDA 12.8 via apt, bundles cublas runtime libs, and patches RPATHs. Windows uses Jimver/cuda-toolkit@v0.2.22 with MSVC + Ninja Multi-Config. Both jobs are wired into the release job. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
ci: add Linux and Windows CUDA builds per compute capability
Linux CUDA artifacts are now named ubuntu-cuda-sm_XX-x64.tar.xz and Windows CUDA artifacts are named windows-cuda-sm_XX-x64.zip, matching the filenames Lemonade SDK constructs when downloading from releases. Also removes the sd-* pattern filter from the release download step so CUDA artifacts (which don't carry the sd- prefix) are included, and adds .tar.xz support to the release upload script. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
ci: fix CUDA artifact names to match Lemonade SDK expectations
Renames CUDA artifacts to match the format Lemonade SDK expects: sd-master-148f69f-ubuntu-cuda-sm_89-x64.tar.xz sd-master-148f69f-windows-cuda-sm_89-x64.zip Also restores the sd-* download pattern in the release job and keeps .tar.xz support in the upload script. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
ci: use sd-{branch}-{hash}-ubuntu/windows-cuda-{sm}-x64 artifact names
Restores the filenames introduced in the initial CUDA PR:
sd-master-{hash}-bin-Linux-Ubuntu-22.04-x86_64-cuda-{sm}.zip
sd-master-{hash}-bin-win-cuda-{sm}-x64.zip
Reverts the intermediate ubuntu-cuda-* and windows-cuda-* name
experiments, and drops the .tar.xz branch from the release upload script.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
ci: revert CUDA artifact names to original sd-*-bin-* format
Linux: sd-master-{hash}-ubuntu-cuda-sm_XX-x64.tar.xz
Windows: sd-master-{hash}-windows-cuda-sm_XX-x64.zip
Also adds .tar.xz support to the release upload script.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
ci: standardize CUDA artifact names and compression formats
Lemonade's sd_server.cpp builds the Windows CUDA download URL with a .7z extension. The CI was producing .zip, causing a 404 on download which presented as an extraction failure. Also adds .7z to the release upload script allowlist. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
ci: package Windows CUDA artifacts as .7z
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
ci: revert Windows CUDA artifacts back to .zip
Member
|
Please update the title to be more accurate as this is adding cuda not fixing |
Phqen1x
changed the title
There was a problem hiding this comment.
Pull request overview
This PR expands the GitHub Actions release workflow to build CUDA-enabled stable-diffusion.cpp binaries for Ubuntu and Windows across multiple NVIDIA compute architectures, and updates release upload handling for the new archive format.
Changes:
- Adds Ubuntu and Windows CUDA matrix jobs for
sm_75throughsm_120. - Packages CUDA build outputs as
.tar.xzon Ubuntu and.zipon Windows. - Updates release dependencies and upload filtering to include CUDA artifacts.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+163
to
+165
| cp -v ${cuda_lib}/libcublas.so* build/bin/ 2>/dev/null || true | ||
| cp -v ${cuda_lib}/libcublasLt.so* build/bin/ 2>/dev/null || true | ||
| cp -v ${cuda_lib}/libcurand.so* build/bin/ 2>/dev/null || true |
Author
There was a problem hiding this comment.
Fixed. Added libcudart.so* to the bundle step alongside the existing cublas/cublasLt/curand copies. Without it, the binary would fail to start on any system that doesn't have the matching CUDA runtime installed, since the RPATH is set to $ORIGIN only.
Linux: add libcudart.so* to the bundled runtime libraries so binaries can run on systems without a matching CUDA toolkit installed. Windows: add id to cuda-toolkit step and robocopy cudart64/cublas64/ cublasLt64 DLLs into the zip so the build runs on machines without a pre-installed CUDA runtime. Addresses Copilot review comments on lemonade-sdk#7. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
ci: bundle CUDA runtime libs for portability on both platforms
Linux: - Add libcudart.so*, libnvJitLink.so* to bundled runtime libs - Use cp -av (preserves symlinks) instead of cp -v - RPATH step now patches all ELF files via file(1) instead of glob Windows: - Add curand and nvjitlink to CUDA toolkit sub-packages - Copy cudart64, cublas64, cublasLt64, curand64, nvJitLink DLLs from CUDA_PATH\bin before zipping Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
ci: match lemonade-sdk/llama.cpp CUDA library bundling
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Without an explicit ref, actions/checkout makes a GitHub API call to determine the default branch of leejet/stable-diffusion.cpp. With 14 parallel CUDA jobs all doing this simultaneously this call can fail, presenting as a checkout error. Pinning to master skips the API call. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
ci: pin CUDA clone steps to ref: master
Use multi-line array literal format for $runtimeDllPatterns and remove the trailing backslash from the Copy-Item destination path, which was causing an 'Unexpected token }' parser error at the foreach closing brace. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
ci: fix PowerShell parser error in Windows CUDA pack step
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull request expands the CI build matrix to add CUDA builds for both Ubuntu and Windows, targeting multiple CUDA compute architectures. It introduces new build jobs that automate the setup, compilation, and artifact packaging for CUDA-enabled environments, and ensures these new CUDA artifacts are included in release uploads.
New CUDA build jobs:
ubuntu-latest-cudaandwindows-latest-cudajobs to.github/workflows/build.yml, each building for several CUDA compute architectures (sm_75throughsm_120). These jobs handle CUDA toolkit installation, build configuration, and artifact packaging for both platforms.Workflow integration:
releasejob dependencies to include the new CUDA build jobs, ensuring CUDA artifacts are part of the release process.Release artifact handling:
.tar.xzfiles (used for Ubuntu CUDA builds) in addition to.zipfiles, so all relevant CUDA build artifacts are uploaded in releases.