.github/workflows · llama-cpp-bonsai · Tangled

llama-cpp-bonsai

llama.cpp fork for Ternary Bonsai 2 27B: MTP speculation, suffix cache reuse (SCR), q8 KV, two-slot fairness, fused DeltaNet kernels

llama-cpp-bonsai .github workflows

52 files

bri-prism · release: ship CPU backend variants in the CUDA and HIP bundles (#241) (#271) · 1mo ago

ai : update gh permissions (#20895)

bench.yml.disabled

llama : move end-user examples to tools directory (#13249)

build-3rd-party.yml

common : fix env names to all have LLAMA_ARG_ prefix (#23778)

build-and-test-snapdragon.yml

snapdragon: bump toolchain docker to v0.7 to fix ui build issues (#23680)

build-android.yml

ci: install only platform-tools with setup-android (legacy 'tools' package is gone) (#175)

build-apple.yml

ci : apply ccache-clear with older/min/dry-run to all ccache jobs (#27602)

build-cache.yml

ci : Update OpenVINO to 2026.3, skip nemotron-h rollback test (#27292)

common : fix env names to all have LLAMA_ARG_ prefix (#23778)

build-cmake-pkg.yml

ci: use shell script to check cmake pkg (#27414)

ci : apply ccache-clear with older/min/dry-run to all ccache jobs (#27602)

build-cross.yml

ci : reduce (disable SYCL and CANN builds/releases) (#23705)

build-cuda-ubuntu.yml

ci : apply ccache-clear with older/min/dry-run to all ccache jobs (#27602)

build-cuda-windows.yml

ci: add Windows ARM64 CUDA support to the manual workflow (#27300)

common : fix env names to all have LLAMA_ARG_ prefix (#23778)

ci : build-msys job slimming [no ci] (#24157)

build-opencl.yml

ci : apply ccache-clear with older/min/dry-run to all ccache jobs (#27602)

build-openvino.yml

ci : apply ccache-clear with older/min/dry-run to all ccache jobs (#27602)

build-riscv.yml

ci : refactor (#23789)

build-sanitize.yml

ci: fix thread sanitizer + remove ccache (#26927)

build-self-hosted.yml

ci : Update OpenVINO to 2026.3, skip nemotron-h rollback test (#27292)

ci : apply ccache-clear with older/min/dry-run to all ccache jobs (#27602)

build-virtgpu.yml

ggml-virtgpu: Add a GHA build check (#22943)

build-vulkan.yml

ci : apply ccache-clear with older/min/dry-run to all ccache jobs (#27602)

ci : apply ccache-clear with older/min/dry-run to all ccache jobs (#27602)

build-webgpu.yml

ci : apply ccache-clear with older/min/dry-run to all ccache jobs (#27602)

check-vendor.yml

ci : move most slim jobs to self-hosted runners (#23619)

close-issue.yml

ci: Also exempt 'security' tag from auto-close (#21844)

ci : move most slim jobs to self-hosted runners (#23619)

copilot-setup-steps.yml

ci : limit requirements versions (#20980)

ci : add attestation for signed release artifacts (#25933)

editorconfig.yml

ci : move most slim jobs to self-hosted runners (#23619)

gguf-publish.yml

gguf-py : bump version to 0.19.0 (#22664)

hip-quality-check.yml

ci : apply ccache-clear with older/min/dry-run to all ccache jobs (#27602)

ci : use new 1vCPU runner for lightweight jobs (#19107)

make-release.yml

ci : fix empty release_id in make-release upload step (#27516)

pr-draft-label.yml

ci: add pr-draft-label (#26801)

pre-tokenizer-hashes.yml

ci : fix pre-tokenizer-hashes check (#23651)

python-check-requirements.yml

ci : move most slim jobs to self-hosted runners (#23619)

python-lint.yml

ci : move most slim jobs to self-hosted runners (#23619)

python-type-check.yml

ci : move most slim jobs to self-hosted runners (#23619)

release-prism.yml

release: ship CPU backend variants in the CUDA and HIP bundles (#241) (#271)

ci : Restore ROCm job for Ubuntu (#27399)

server-sanitize.yml

tests : clean-up server test, use `tests.sh` in ci (#26886)

server-self-hosted.yml

tests : clean-up server test, use `tests.sh` in ci (#26886)

ci : apply ccache-clear with older/min/dry-run to all ccache jobs (#27602)

ui-build-self-hosted.yml

server: clean up static assets handling (#24550)

server: clean up static assets handling (#24550)

server: remove loading.html (#25500)

ui-self-hosted.yml

ui: PWA support (#23871)

ui: PWA support (#23871)

update-ops-docs.yml

ci : move most slim jobs to self-hosted runners (#23619)

cmake : introduce semantic versioning (#26839)