637 Commits
Author SHA1 Message Date
Sreeram b115a6333c Merge pull request #21 from lemonade-sdk/sreeram/add-rocm-10.2-builds master-1106-b115a63 2026-11-19 16:21:55 -08:00
Sreeram f660cb0ae8 Add ROCm 10.2.0 builds and stop one ROCm version from cancelling or withholding the others 2026-11-19 12:53:37 -08:00
Sreeram f1bcbc4c9b Merge pull request #20 from lemonade-sdk/sreeram/pin-linux-ubuntu-24.04 2026-11-18 21:08:24 -08:00
Sreeram 0d18143f31 ci: pin Linux CPU/Vulkan builds to Ubuntu 24.04 and drop retired macos-14 leg 2026-11-18 16:53:09 -08:00
Sreeram 90e86d183d Add ROCm 10.1.0 builds (#19) master-1091-90e86d1 master-1096-90e86d1 master-1022-90e86d1 master-1024-90e86d1 master-1029-90e86d1 master-1031-90e86d1 master-1039-90e86d1 master-1043-90e86d1 master-1047-90e86d1 master-1050-90e86d1 master-1052-90e86d1 master-1053-90e86d1 master-1056-90e86d1 master-1068-90e86d1 master-1079-90e86d1 master-1088-90e86d1 master-1017-90e86d1 master-1000-90e86d1 master-1104-90e86d1 master-1106-90e86d1 master-1015-90e86d1 master-995-90e86d1 master-987-90e86d1 master-982-90e86d1 master-977-90e86d1 master-973-90e86d1 master-968-90e86d1 master-965-90e86d1 master-964-90e86d1 master-957-90e86d1 master-1006-90e86d1 2026-10-09 13:13:33 -05:00
Harkirat Gill f5df645e22 ci: bundle HIP runtime libraries with Windows ROCm release (#18) master-945-f5df645 master-935-f5df645 master-929-f5df645 2026-10-02 14:13:27 -05:00
Mario Limonciello (AMD) 017cc8e5b5 Fix ROCm ccache build caching
Using mtime doesn't work with wheels, need to compare content.
master-882-017cc8e master-866-017cc8e master-917-017cc8e master-908-017cc8e master-900-017cc8e master-894-017cc8e master-889-017cc8e master-929-017cc8e master-877-017cc8e master-872-017cc8e master-870-017cc8e master-920-017cc8e master-859-017cc8e master-853-017cc8e master-849-017cc8e master-846-017cc8e master-841-017cc8e master-921-017cc8e master-831-e2329c3 master-831-017cc8e
2026-08-27 09:19:49 -05:00
Mario Limonciello 879c67a96f Update ROCm to 10.0 release 2026-08-27 09:18:42 -05:00
Ken VanDine e2329c3722 Merge pull request #17 from lemonade-sdk/ci/cuda-improvements
ci: CUDA build improvements
master-814-e2329c3 master-820-e2329c3 master-817-e2329c3 master-830-e2329c3 master-812-e2329c3 master-810-e2329c3 master-809-e2329c3 master-805-e2329c3 master-802-e2329c3 master-798-e2329c3 master-827-e2329c3
2026-07-28 23:21:08 -04:00
Ken VanDineandClaude Opus 5 aeaf146d5c ci: install only the CUDA components the Linux builds use
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]>
2026-07-28 22:07:42 -04:00
Ken VanDineandClaude Opus 5 382f9e0c9b ci: CUDA build improvements
Two changes, both measured against run 30332616539.

Cache the windows-latest-cmake build. Its cuda12 leg compiles nine CUDA
architectures in a single job and had no ccache step at all, making it
the second-longest job in the run at 90.6 min of Build. windows-latest-cuda
runs the same MSVC/Ninja/Release setup with ccache and averages 1.6 min
per leg at 97.96% hit rate. No cmake flags are needed: ggml's
src/CMakeLists.txt sets RULE_LAUNCH_COMPILE when it finds ccache on PATH
(GGML_CCACHE defaults to ON), which is how windows-latest-cuda already
gets its hits. The cuda12 leg gets max-size 2G because nine
architectures plus GGML_CPU_ALL_VARIANTS will not fit the 500M default
that suits the cpu and vulkan legs.

Parallelize xz when packing the Linux CUDA artifacts. tar -cJf drives a
single-threaded xz and was the largest cost in those jobs, 50.9 min
across the eight x64 legs plus 5.9 min on arm64, against only 12.8 min
of Build. Measured on a 2.9 GB binary payload: 12m41s single-threaded
versus 47.7s on 32 cores, with the archive 1.8% larger because threaded
mode compresses independent blocks. The runners are 4-core, so expect
roughly 3-4x there.

ccache itself was already healthy everywhere it was configured, at
98-100% hit rates, and the release job's artifact download is fine on a
full ubuntu-latest VM. Neither needed changing.

Co-Authored-By: Claude Opus 5 <[email protected]>
2026-07-28 22:01:27 -04:00
Mario Limonciello 65745b48ed Attempt to align to upstream jobs master-789-65745b4 master-796-65745b4 master-798-65745b4 master-795-65745b4 master-788-65745b4 2026-07-22 16:23:54 -05:00
Mario Limonciello d43a5df8d8 Align vulkan job with upstream 2026-07-22 11:11:41 -05:00
Mario Limonciello (AMD) bd6bbfa8f2 Add vulkan jobs master-785-bd6bbfa 2026-07-21 23:29:05 -05:00
Mario Limonciello 506bb58f28 Update workflows for ROCm 7.14 master-785-506bb58 2026-07-21 11:02:16 -05:00
Ken VanDine 9dcaab1489 Merge pull request #14 from lemonade-sdk/fix/validate-release-artifacts
ci: fail release if any expected artifacts are missing
master-782-9dcaab1 master-783-9dcaab1 master-765-9dcaab1 master-779-9dcaab1 master-775-9dcaab1 master-773-9dcaab1 master-769-9dcaab1 master-768-9dcaab1 master-743-9dcaab1 master-746-9dcaab1 master-749-9dcaab1 master-759-9dcaab1
2026-07-02 16:47:33 +02:00
Ken VanDine efef589d0d Merge remote-tracking branch 'refs/remotes/origin/fix/validate-release-artifacts' into fix/validate-release-artifacts 2026-07-02 10:32:06 -04:00
Ken VanDineandClaude Sonnet 5 6296594e1b ci: prune stale release assets from families dropped in the current run
The release is reused across runs against the same tag (idempotent
create-or-get). If a family (e.g. rocm-therock) was complete and
published in an earlier run but the current run finds it incomplete and
drops it locally, its assets from that earlier run were never removed —
the release would keep looking complete for a family this run couldn't
actually reproduce.

The upload step now reconciles existing release assets against the
current ./artifact file set: anything not fully uploaded (a broken
partial upload, as before) or not present in this run's file set (stale
leftovers from a dropped family) gets deleted before uploading.

Addresses review feedback on lemonade-sdk/stable-diffusion.cpp#14. The
always() fix requested in the same review was already applied in
03e249d.

Co-Authored-By: Claude Sonnet 5 <[email protected]>
2026-07-02 10:31:42 -04:00
Ken VanDineandClaude Sonnet 5 40969fbb32 ci: run release job even when a build job fails
Without always(), GitHub Actions' default skip-if-a-needed-job-failed
behavior meant a single failed build job (e.g. one CUDA sm_* matrix leg,
several of which use fail-fast: false) could skip the release job
outright, before the per-family completeness check ever ran — silently
producing no release instead of a correct partial one.

The other issue found in the equivalent llama.cpp fix (a hard-fail step
that could block unrelated families) doesn't apply here: this workflow
has no cross-job merge step comparable to llama.cpp's Windows CPU-into-
other-zips step, so there's nothing else that needs the same treatment.

Follow-up to #14.

Co-Authored-By: Claude Sonnet 5 <[email protected]>
2026-07-02 10:31:42 -04:00
Ken VanDineandClaude Sonnet 5 f41bf4f420 ci: fail release if expected artifacts are missing, per backend family
Port the artifact-completeness gate from lemonade-sdk/llama.cpp#16 to
this repo's release job, adapted to its build matrix:

- cuda: 8 sm_* variants on ubuntu x64 + windows x64, plus sm_121-only
  on ubuntu arm64 (GB10) — 17 files total.
- rocm-therock: TheRock nightly ROCm 7.13.0 on windows + ubuntu.
- rocm-hipsdk: official/legacy HIP SDK ROCm on windows (7.1.1) +
  ubuntu (7.2.1) — kept separate from rocm-therock since they're
  different SDKs, not just different platforms of the same backend.
- cpu: ubuntu + windows avx2 builds.
- metal: macos-14 + macos-latest builds.

Each family is all-or-nothing: if any artifact in a family is
missing, every artifact for that family is dropped from the release
so a release never contains a partial/inconsistent set (e.g. CUDA
split across sm_* or platforms). Other families are unaffected by a
gap in one. A release with zero artifacts overall is never created.

Also brings the release/upload mechanism up to parity with
llama.cpp's: an idempotent create-or-get-release step (safe to
re-run after a partial failure) and a retrying, resumable asset
upload, replacing the old anzz1/action-create-release +
github-script@v3 flow.

Co-Authored-By: Claude Sonnet 5 <[email protected]>
2026-07-02 10:31:42 -04:00
Ken VanDine 1206d2da21 Merge pull request #15 from lemonade-sdk/fix/windows-cuda-bigobj
ci(windows-cuda): pass /bigobj to fix C1128 build failure
2026-07-02 16:30:15 +02:00
Ken VanDineandClaude Sonnet 5 bd5e37fcb9 ci: prune stale release assets from families dropped in the current run
The release is reused across runs against the same tag (idempotent
create-or-get). If a family (e.g. rocm-therock) was complete and
published in an earlier run but the current run finds it incomplete and
drops it locally, its assets from that earlier run were never removed —
the release would keep looking complete for a family this run couldn't
actually reproduce.

The upload step now reconciles existing release assets against the
current ./artifact file set: anything not fully uploaded (a broken
partial upload, as before) or not present in this run's file set (stale
leftovers from a dropped family) gets deleted before uploading.

Addresses review feedback on lemonade-sdk/stable-diffusion.cpp#14. The
always() fix requested in the same review was already applied in
03e249d.

Co-Authored-By: Claude Sonnet 5 <[email protected]>
2026-07-02 10:00:29 -04:00
Ken VanDine bd1c5f2d43 ci(windows-cuda): pass /bigobj to fix C1128 build failure
stable-diffusion.cpp's Windows CUDA build fails with:

  fatal error C1128: number of sections exceeded object file format
  limit: compile with /bigobj

src/stable-diffusion.cpp combined with the CUDA backend's generated
code exceeds MSVC's default COFF section limit per object file. The
windows-latest-cmake job already works around the same class of issue
with -DCMAKE_CXX_FLAGS='/bigobj'; apply the same flag to the CUDA
build.
2026-07-02 09:42:22 -04:00
Ken VanDineandClaude Sonnet 5 03e249db83 ci: run release job even when a build job fails
Without always(), GitHub Actions' default skip-if-a-needed-job-failed
behavior meant a single failed build job (e.g. one CUDA sm_* matrix leg,
several of which use fail-fast: false) could skip the release job
outright, before the per-family completeness check ever ran — silently
producing no release instead of a correct partial one.

The other issue found in the equivalent llama.cpp fix (a hard-fail step
that could block unrelated families) doesn't apply here: this workflow
has no cross-job merge step comparable to llama.cpp's Windows CPU-into-
other-zips step, so there's nothing else that needs the same treatment.

Follow-up to #14.

Co-Authored-By: Claude Sonnet 5 <[email protected]>
2026-07-02 09:39:12 -04:00
Ken VanDineandClaude Sonnet 5 15ba36d3e6 ci: fail release if expected artifacts are missing, per backend family
Port the artifact-completeness gate from lemonade-sdk/llama.cpp#16 to
this repo's release job, adapted to its build matrix:

- cuda: 8 sm_* variants on ubuntu x64 + windows x64, plus sm_121-only
  on ubuntu arm64 (GB10) — 17 files total.
- rocm-therock: TheRock nightly ROCm 7.13.0 on windows + ubuntu.
- rocm-hipsdk: official/legacy HIP SDK ROCm on windows (7.1.1) +
  ubuntu (7.2.1) — kept separate from rocm-therock since they're
  different SDKs, not just different platforms of the same backend.
- cpu: ubuntu + windows avx2 builds.
- metal: macos-14 + macos-latest builds.

Each family is all-or-nothing: if any artifact in a family is
missing, every artifact for that family is dropped from the release
so a release never contains a partial/inconsistent set (e.g. CUDA
split across sm_* or platforms). Other families are unaffected by a
gap in one. A release with zero artifacts overall is never created.

Also brings the release/upload mechanism up to parity with
llama.cpp's: an idempotent create-or-get-release step (safe to
re-run after a partial failure) and a retrying, resumable asset
upload, replacing the old anzz1/action-create-release +
github-script@v3 flow.

Co-Authored-By: Claude Sonnet 5 <[email protected]>
2026-07-02 09:23:26 -04:00
Ken VanDine db4801452e Merge pull request #13 from lemonade-sdk/kenvandine/arm64_cuda
ci: add sm_121 (GB10) CUDA arch for x86 and arm64
master-696-db48014 master-741-db48014 master-737-db48014 master-726-db48014 master-722-db48014 master-721-db48014 master-719-db48014 master-714-db48014 master-710-db48014 master-707-db48014 master-703-db48014 master-691-db48014 master-685-db48014
2026-06-11 23:17:25 +02:00
Ken VanDineandCopilot Autofix powered by AI 8cd9abef0f Potential fix for pull request finding
Co-authored-by: Copilot Autofix powered by AI <[email protected]>
2026-06-11 17:16:58 -04:00
Ken VanDineandCopilot 9e10190500 ci: bump Jimver/cuda-toolkit to v0.2.35 with CUDA 12.9.1
v0.2.22 does not include CUDA 12.9.x; v0.2.24 was the first release to
add it. Bump to latest v0.2.35 and use 12.9.1 (latest 12.9 patch).

Co-authored-by: Copilot <[email protected]>
2026-06-11 16:45:10 -04:00
Ken VanDineandCopilot f19563e9e3 ci: upgrade CUDA to 12.9 for sm_121 support
sm_121 (GB10/Blackwell) requires CUDA 12.9. Update ubuntu-latest-cuda,
windows-latest-cuda, and ubuntu-arm64-cuda jobs accordingly.

Co-authored-by: Copilot <[email protected]>
2026-06-11 16:15:03 -04:00
Ken VanDineandCopilot a8ec287fa5 ci: add sm_121 (GB10) CUDA arch for x86 and arm64
- Add sm_121 to ubuntu-latest-cuda and windows-latest-cuda matrices
- Add new ubuntu-arm64-cuda job targeting ubuntu-24.04-arm runner with sm_121
- Use CUDA sbsa (ARM64) package repo for arm64 CUDA Toolkit install
- Add ubuntu-arm64-cuda to release job needs

Co-authored-by: Copilot <[email protected]>
2026-06-11 15:29:38 -04:00
Ken VanDine bf6b2efbd1 Merge pull request #12 from kenvandine/windows-cuda-fix
fix(cuda): add -DGGML_CUDA=ON to Windows CUDA build
master-685-bf6b2ef
2026-06-10 04:10:20 +02:00
Ken VanDineandCopilot fb10de9a5c fix(cuda): add -DGGML_CUDA=ON to Windows CUDA build
The Windows CUDA cmake invocation was missing -DGGML_CUDA=ON, which
meant the ggml CUDA backend was never compiled in. Without it, the
build silently falls back to CPU even when the CUDA toolkit is
installed. This is the same fix already applied to the Linux CUDA
build in commit 6a68a98.

Fixes: lemonade-sdk/lemonade#2171 (sdcpp:cuda falls back to CPU on Windows + RTX 4090)

Co-authored-by: Copilot <[email protected]>
2026-06-09 21:42:34 -04:00
Ken VanDine b638fe9228 Merge pull request #11 from Phqen1x/lemonade
Standardize and fix CUDA artifact naming and packaging
master-679-b638fe9 master-685-b638fe9 master-672-b638fe9
2026-06-05 17:03:03 +02:00
Drew VanDine 2de7212d11 Merge pull request #13 from Phqen1x/fix-cuda-bundling
Fix cuda bundling
2026-06-05 09:09:10 -04:00
Drew VanDineandClaude Sonnet 4.6 6a68a98599 ci: fix CUDA compilation and bundle all ggml shared libs
Add -DGGML_CUDA=ON and -DCMAKE_CUDA_COMPILER explicitly to the Linux
CUDA cmake invocation so CUDA is actually compiled instead of silently
falling back to CPU when auto-detection fails.

Widen the ggml artifact collection from libggml-cuda.so only to
libggml*.so* (Linux) and ggml*.dll (Windows) to capture all ggml shared
libraries (core, base backend, cuda backend) regardless of where cmake
places them in the build tree.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>
2026-06-05 09:08:23 -04:00
Ken VanDine c2cc188ff3 Merge pull request #10 from Phqen1x/bundle-ggml-cuda
ci: bundle libggml-cuda.so/ggml-cuda.dll in CUDA release artifacts
master-672-c2cc188
2026-06-04 22:35:49 +02:00
Drew VanDineandClaude Sonnet 4.6 df4efd59c6 ci: bundle libggml-cuda.so/ggml-cuda.dll in CUDA release artifacts
The ggml CUDA backend is built as a shared library plugin when
SD_BUILD_SHARED_LIBS=ON. Bundle it alongside the CUDA runtime libs so
that CUDA inference works out of the box without the plugin being
missing at runtime.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>
2026-06-04 16:22:51 -04:00
Ken VanDine e3937d9654 Merge pull request #8 from kenvandine/add_ci_check
ci: validate release build on pull requests
master-672-e3937d9 master-669-e3937d9 master-666-e3937d9
2026-06-01 14:43:50 +02:00
Ken VanDine c00c8b87dc Merge pull request #9 from lemonade-sdk/copilot/fix-code-review-comment
ci: scope `contents: write` to release job only
2026-06-01 14:42:55 +02:00
copilot-swe-agent[bot] c3af5c187b Fix: use least-privilege permissions in CI workflow 2026-06-01 12:41:37 +00:00
copilot-swe-agent[bot] c6ebd5f180 Initial plan 2026-06-01 12:39:46 +00:00
Ken VanDineandClaude Opus 4.8 429bf57c94 ci: validate release build on pull requests
Add a pull_request trigger to build.yml so the release build is
validated on PRs, mirroring lemonade-sdk/llama.cpp. The pack/upload
and release jobs remain gated on schedule/create_release, so nothing
is published on a PR run.

Scope the trigger to the workflow file itself: the build jobs clone
source from upstream (leejet/stable-diffusion.cpp), so only changes
to this workflow can affect a PR run's outcome.

On PRs, the CUDA matrices build a single representative arch (sm_89)
instead of all seven; packaging logic is identical across sm_*, and
the full matrix still runs on schedule/dispatch.

Co-Authored-By: Claude Opus 4.8 <[email protected]>
2026-06-01 07:41:33 -04:00
Ken VanDine da0c3b3764 Merge pull request #7 from Phqen1x/lemonade
Adding CUDA Support for stable-diffusion.cpp
2026-06-01 13:28:36 +02:00
Drew VanDine c0335cf7a0 Merge pull request #11 from Phqen1x/fix-powershell-parser
ci: fix PowerShell parser error in Windows CUDA pack step
2026-05-31 23:14:14 -04:00
copilot-swe-agent[bot] 9cffd0da35 Merge origin/lemonade into fix-powershell-parser 2026-06-01 03:10:30 +00:00
Drew VanDineandClaude Sonnet 4.6 7437d050c0 ci: fix PowerShell parser error in Windows CUDA pack step
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 <[email protected]>
2026-05-31 23:07:24 -04:00
Drew VanDine 3930b7bc5b Merge pull request #10 from Phqen1x/fix-cuda-clone-ref
ci: pin CUDA clone steps to ref: master
2026-05-31 22:55:33 -04:00
Drew VanDineandClaude Sonnet 4.6 fa19b4115b ci: pin CUDA clone steps to ref: master
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 <[email protected]>
2026-05-31 22:53:11 -04:00
Ken VanDineandCopilot Autofix powered by AI 73bb113fc7 Potential fix for pull request finding
Co-authored-by: Copilot Autofix powered by AI <[email protected]>
2026-05-31 22:38:08 -04:00
Drew VanDine fc97199a70 Merge pull request #9 from Phqen1x/match-lemonade-cuda-bundling
ci: match lemonade-sdk/llama.cpp CUDA library bundling
2026-05-31 22:11:13 -04:00