Skip to content

ci: add build-llama workflow (patched R-SWA llama-server) - #1

Merged
whit3rabbit merged 1 commit into
mainfrom
ci/build-llama
Jul 4, 2026
Merged

ci: add build-llama workflow (patched R-SWA llama-server)#1
whit3rabbit merged 1 commit into
mainfrom
ci/build-llama

Conversation

@whit3rabbit

Copy link
Copy Markdown
Owner

Adds .github/workflows/build-llama.yml: a manual (workflow_dispatch) job that builds llama-server from the unmerged llama.cpp PR #24975 (Unlimited-OCR R-SWA) for macOS arm64/x64, Linux x64, Windows x64, repackages each as .zip, and publishes them to a dedicated llama-rswa-<date> prerelease.

Why merge this first: workflow_dispatch workflows are only runnable once the file is on the default branch. This PR only adds the workflow (no other changes); the source/PINS changes that consume its output are a separate follow-up.

After merge: run Actions → build-llama with llama_commit=649864fc6ba2fee8b7800b819808b94ef609dc9e and release_tag=llama-rswa-<date>, then fill the four sha256s into src/tools/mod.rs.

🤖 Generated with Claude Code

Builds llama-server from the unmerged llama.cpp PR #24975 (Unlimited-OCR
R-SWA) for macOS arm64/x64, Linux x64, Windows x64; repackages each as .zip
and publishes to a dedicated llama-rswa-<date> prerelease. Manual dispatch;
pins an exact commit SHA for reproducibility.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@whit3rabbit
whit3rabbit merged commit ae544bc into main Jul 4, 2026
3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant