Search Criteria
Package Details: stable-diffusion.cpp-cublas-git r919.19bbbca-1
Package Actions
| Git Clone URL: | https://aur.archlinux.org/stable-diffusion.cpp-cublas-git.git (read-only, click to copy) |
|---|---|
| Package Base: | stable-diffusion.cpp-cublas-git |
| Description: | Stable Diffusion in pure C/C++ (with NVIDIA CUDA optimizations) |
| Upstream URL: | https://github.com/leejet/stable-diffusion.cpp |
| Licenses: | MIT |
| Conflicts: | stable-diffusion.cpp, stable-diffusion.cpp-cublas |
| Provides: | stable-diffusion.cpp, stable-diffusion.cpp-cublas |
| Submitter: | robertfoster |
| Maintainer: | yataro |
| Last Packager: | yataro |
| Votes: | 1 |
| Popularity: | 0.000175 |
| First Submitted: | 2025-04-12 14:27 (UTC) |
| Last Updated: | 2026-09-30 17:00 (UTC) |
Dependencies (6)
- cuda (cuda11.1AUR, cuda-12.2AUR, cuda12.0AUR, cuda11.4AUR, cuda-12.5AUR, cuda-12.8AUR, cuda-pascalAUR, cuda-12.9AUR, cuda-12.6AUR)
- libwebp (libwebp-gitAUR)
- cmake (cmake3AUR, cmake-gitAUR) (make)
- git (git-gitAUR, git-glAUR, git-wd40AUR) (make)
- ninja (ninja-gitAUR, ninja-memAUR, ninja-noemacs-gitAUR, ninja-kitwareAUR, ninja-fuchsia-gitAUR, n2-gitAUR) (make)
- pnpm (pnpm-corepackAUR, pnpm-gitAUR) (make)
Required by (1)
- koharu-bin (requires stable-diffusion.cpp) (optional)
Latest Comments
yataro commented on 2026-09-30 17:01 (UTC)
Sorry, busy week. Forgot to actually push it.
Enverex commented on 2026-09-29 20:26 (UTC)
I always do clean builds, just-in-case. Still seeing the same behaviour now though.
yataro commented on 2026-09-25 11:29 (UTC)
Please, do a clean build if you did build it before. Upstream source for GGML is changed.
yataro commented on 2026-09-25 09:10 (UTC)
@Enverex, yes, upstream switched to their own GGML fork, I'll update it later today. Thanks for the heads up.
Enverex commented on 2026-09-24 16:53 (UTC)
Seems to be failing to build for me:
Cloning into '/var/tmp/stable-diffusion.cpp-cublas-git/src/stable-diffusion.cpp-cublas/examples/server/frontend'... done. Cloning into '/var/tmp/stable-diffusion.cpp-cublas-git/src/stable-diffusion.cpp-cublas/ggml'... done. Cloning into '/var/tmp/stable-diffusion.cpp-cublas-git/src/stable-diffusion.cpp-cublas/thirdparty/libwebm'... done. Skipping submodule 'thirdparty/libwebp' Submodule path 'examples/server/frontend': checked out 'c4bce3d6b3f236614cca21014f076083b7270ba8' fatal: git upload-pack: not our ref 4bf5f6000653b7881d00963cd6ddb665ccd62a8d fatal: remote error: upload-pack: not our ref 4bf5f6000653b7881d00963cd6ddb665ccd62a8d fatal: Fetched in submodule path 'ggml', but it did not contain 4bf5f6000653b7881d00963cd6ddb665ccd62a8d. Direct fetching of that commit failed. ==> ERROR: A failure occurred in prepare().yataro commented on 2026-05-19 09:28 (UTC)
Package has been refactored, I simplified PKGBUILD and adjusted missing dependencies for frontend build. The package now correctly installs the shared stable‑diffusion library, which also led to a nearly x2 size reduction because previously sd‑cli and sd‑server were linked with a static one.
Davidyz commented on 2026-05-07 07:12 (UTC)
The build fails with the recent upgrade of gcc16. The current PKGBUILD hardcode nvcc to use gcc, which now points to gcc16. It's probably related to cuda not supporting gcc16 yet.
Suggested fix: change the
gccin makedeps togcc15(it's now in the officialextrarepo) and remove the hardcodedNVCC_CCBIN="gcc"in thebuild()function. This will make nvcc honour theNVCC_CCBIN="/usr/bin/g++-15"setting in/etc/profile.d/cuda.shprovided by thecudapackage, and should hopefully fix the building.mven commented on 2025-04-28 01:05 (UTC)
I'm also experiencing the same error @dcNdrew. It's currently preventing me from making this package.
DcNdrew commented on 2025-04-25 17:58 (UTC)
There is an error. error: too few arguments to function ‘ggml_tensor ggml_upscale_ext(ggml_context, ggml_tensor*, int, int, int, int, ggml_scale_mode)’