mirror of
https://github.com/lemonade-sdk/stable-diffusion.cpp.git
synced 2026-11-22 00:55:10 -10:00
ci/cuda-improvements
Both Linux CUDA jobs installed the cuda-toolkit-12-9 metapackage, which apt reports as 3935 MB of archives per job. That is 16 jobs per nightly run on the x64 matrix plus the arm64 leg, and it made "Install CUDA Toolkit" the second-largest cost in those jobs at 36.5 min across the x64 legs. Most of it is never used. The metapackage pulls Nsight Systems and Compute, cuFFT, cuSPARSE, cuSOLVER and NPP; ggml-cuda links only CUDA::cudart, CUDA::cublas and CUDA::cuda_driver plus CCCL for thrust/cub, and stable-diffusion.cpp links only ggml. Install that subset instead, ~595 MB of direct archives, and add a guard that names the missing file if NVIDIA ever repackages one of them rather than failing partway through the compile. Package names verified present in both developer.download.nvidia.com repos the jobs use, ubuntu2204/x86_64 and ubuntu2404/sbsa. The Windows CUDA installs already select sub-packages through Jimver/cuda-toolkit and were left alone. Co-Authored-By: Claude Opus 5 <[email protected]>
Lemonade Stable diffusion fork
This repo is a "Github actions only" fork of stable diffusion that is built with more ROCm releases than upstream stable diffusion supports.
These are built for the purpose of lemonade use, but they can be utilized by any project. Releases just need to be used with matching AMD ROCm SDK releases.
Cadence
The builds are triggered nightly, or can optionally be triggered on demand as well.
Description
Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++
171 MiB
0 Stars
1 Watchers
0 Forks
Releases
1
master-1106-b115a63
Latest