Default branch

master
Some checks failed
GPU tests / ubuntu-latest (1.21.x) (push) Has been cancelled
Security Scan / tests (push) Has been cancelled
Build test / launcher-build-darwin (push) Has been cancelled
build container images / core-image-build (ubuntu:24.04, vulkan, --jobs=4 --output-sync=target, amd64, linux/amd64, ubuntu-latest, false, auto, -gpu-vulkan, noble, 2404) (push) Has been cancelled
Explorer deployment / build-linux (push) Has been cancelled
build container images / hipblas-jobs (rocm/dev-ubuntu-24.04:7.2.1, hipblas, --jobs=3 --output-sync=target, linux/amd64, ubuntu-latest, auto, -gpu-hipblas, noble, 2404) (push) Has been cancelled
build container images / core-image-build (intel/oneapi-basekit:2025.3.2-0-devel-ubuntu24.04, intel, --jobs=3 --output-sync=target, linux/amd64, ubuntu-latest, auto, -gpu-intel, noble, 2404) (push) Has been cancelled
build container images / core-image-build (ubuntu:22.04, cublas, 13, 0, --jobs=4 --output-sync=target, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13, noble, 2404) (push) Has been cancelled
build container images / core-image-build (ubuntu:24.04, , --jobs=4 --output-sync=target, amd64, linux/amd64, ubuntu-latest, false, auto, , noble, 2404) (push) Has been cancelled
build container images / core-image-build (ubuntu:24.04, vulkan, --jobs=4 --output-sync=target, arm64, linux/arm64, ubuntu-24.04-arm, false, auto, -gpu-vulkan, noble, 2404) (push) Has been cancelled
build container images / gh-runner (nvcr.io/nvidia/l4t-jetpack:r36.4.0, cublas, 12, 0, --jobs=4 --output-sync=target, linux/arm64, ubuntu-24.04-arm, true, auto, -nvidia-l4t-arm64, jammy, 2204) (push) Has been cancelled
build container images / gh-runner (ubuntu:24.04, cublas, 13, 0, --jobs=4 --output-sync=target, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-arm64-cuda-13, noble, 2404) (push) Has been cancelled
Build test / launcher-build-linux (push) Has been cancelled
Build test / build-test (push) Has been cancelled
generate and publish intel docker caches / generate_caches (intel/oneapi-basekit:2025.3.2-0-devel-ubuntu24.04, linux/amd64, arc-runner-set) (push) Has been cancelled
lint / golangci-lint (push) Has been cancelled
Tests extras backends / detect-changes (push) Has been cancelled
Tests extras backends / tests-llama-cpp-smoke (push) Has been cancelled
tests / tests-linux (1.26.x) (push) Has been cancelled
tests / tests-apple (1.26.x) (push) Has been cancelled
tests-aio / tests-aio (push) Has been cancelled
E2E Backend Tests / tests-e2e-backend (1.25.x) (push) Has been cancelled
UI E2E Tests / tests-ui-e2e (1.26.x) (push) Has been cancelled
build container images / core-image-build (ubuntu:24.04, , --jobs=4 --output-sync=target, arm64, linux/arm64, ubuntu-24.04-arm, false, auto, , noble, 2404) (push) Has been cancelled
build container images / core-image-build (ubuntu:24.04, cublas, 12, 8, --jobs=4 --output-sync=target, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12, noble, 2404) (push) Has been cancelled
build backend container images / generate-matrix (push) Has been cancelled
build container images / core-image-merge (push) Has been cancelled
build container images / gpu-vulkan-image-merge (push) Has been cancelled
build container images / gpu-nvidia-cuda-12-image-merge (push) Has been cancelled
build container images / gpu-nvidia-cuda-13-image-merge (push) Has been cancelled
Tests extras backends / tests-llama-cpp-grpc-transcription (push) Has been cancelled
build backend container images / backend-jobs-multiarch (push) Has been cancelled
build backend container images / backend-jobs-singlearch (push) Has been cancelled
build backend container images / backend-merge-jobs-multiarch (push) Has been cancelled
build backend container images / backend-merge-jobs-singlearch (push) Has been cancelled
build backend container images / backend-jobs-darwin (push) Has been cancelled
Tests extras backends / tests-transformers (push) Has been cancelled
Tests extras backends / tests-rerankers (push) Has been cancelled
Tests extras backends / tests-diffusers (push) Has been cancelled
Tests extras backends / tests-coqui (push) Has been cancelled
Tests extras backends / tests-moonshine (push) Has been cancelled
Tests extras backends / tests-sherpa-onnx-realtime (push) Has been cancelled
Tests extras backends / tests-sherpa-onnx-grpc-transcription (push) Has been cancelled
build container images / gpu-intel-image-merge (push) Has been cancelled
build container images / gpu-hipblas-image-merge (push) Has been cancelled
build container images / nvidia-l4t-arm64-image-merge (push) Has been cancelled
build container images / nvidia-l4t-arm64-cuda-13-image-merge (push) Has been cancelled
Tests extras backends / tests-pocket-tts (push) Has been cancelled
Tests extras backends / tests-qwen-tts (push) Has been cancelled
Tests extras backends / tests-qwen-asr (push) Has been cancelled
Tests extras backends / tests-nemo (push) Has been cancelled
Tests extras backends / tests-voxcpm (push) Has been cancelled
Tests extras backends / tests-liquid-audio (push) Has been cancelled
Tests extras backends / tests-llama-cpp-quantization (push) Has been cancelled
Tests extras backends / tests-llama-cpp-grpc (push) Has been cancelled
Tests extras backends / tests-whisper-grpc-transcription (push) Has been cancelled
Tests extras backends / tests-sherpa-onnx-grpc-tts (push) Has been cancelled
Tests extras backends / tests-ik-llama-cpp-grpc (push) Has been cancelled
Tests extras backends / tests-turboquant-grpc (push) Has been cancelled
Tests extras backends / tests-acestep-cpp (push) Has been cancelled
Tests extras backends / tests-qwen3-tts-cpp (push) Has been cancelled
Tests extras backends / tests-vibevoice-cpp (push) Has been cancelled
Tests extras backends / tests-vibevoice-cpp-grpc-tts (push) Has been cancelled
Tests extras backends / tests-vibevoice-cpp-grpc-transcription (push) Has been cancelled
Tests extras backends / tests-localvqe-grpc-transform (push) Has been cancelled
Tests extras backends / tests-voxtral (push) Has been cancelled
Tests extras backends / tests-kokoros (push) Has been cancelled
Tests extras backends / tests-insightface-grpc (push) Has been cancelled
Tests extras backends / tests-speaker-recognition-grpc (push) Has been cancelled

1a30020a82 · ci(backend-signing): set COSIGN_EXPERIMENTAL=1 for oci-1-1 referrers mode · Updated 2026-05-24 08:21:05 +00:00

Branches

8fbf18490e · fix: remove deprecated cosign bundle flag from backend merge workflow · Updated 2026-05-22 22:16:44 +00:00

13
2

63313dcdb9 · chore(deps): bump qs · Updated 2026-05-22 21:17:01 +00:00

14
1

fd80c9b971 · chore(deps): bump the go_modules group across 1 directory with 8 updates · Updated 2026-05-21 22:16:36 +00:00

22
1

e02078d761 · chore(deps): bump openssl · Updated 2026-05-21 22:05:04 +00:00

22
1

b6fed26271 · chore(turboquant): retreat pin to 4c1c3ac0 to skip fork GPU regression · Updated 2026-05-21 15:54:38 +00:00

31
2
ci/layered-base-images
Some checks failed
Security Scan / tests (push) Has been cancelled

9d42a16c20 · ci: publish base images to ci-cache instead of localai-base · Updated 2026-05-06 15:13:06 +00:00

191
3

50580a84ae · fix(ci): switch apt mirror per runner — azure on github-hosted, kernel.org on self-hosted · Updated 2026-05-03 22:59:26 +00:00

224
0
Included
feat/distributed-multi-replica-per-host
Some checks failed
Security Scan / tests (push) Has been cancelled

3280b9a287 · fix(distributed): per-replica backend logs (store aggregation + UI) · Updated 2026-04-27 20:55:24 +00:00

261
0
Included
feat/buun-llama-cpp-backend
Some checks failed
Security Scan / tests (push) Has been cancelled

9787bee48b · fix(buun-llama-cpp): shim cudaMemcpy{To,From}Symbol + WARP_SIZE on fwht128 shuffles · Updated 2026-04-24 20:09:36 +00:00

306
8

d9d7b5c29b · docs(readme): add April 2026 highlights to Latest News · Updated 2026-04-23 20:47:06 +00:00

314
0
Included

5f7a0c3b26 · chore(turboquant): bump fork pin to rebase/upstream-sync-april-2026 · Updated 2026-04-22 20:01:49 +00:00

328
1

9eb21e9a20 · fix(turboquant): patch ggml-hip CMakeLists to compile new f16-turbo fattn-vec instances · Updated 2026-04-22 07:17:33 +00:00

334
2

798b5b2d84 · chore(turboquant): bump fork to 4d24ad87 and patch ggml-hip for new f16-turbo fattn-vec instances · Updated 2026-04-22 07:13:47 +00:00

332
1

b27de08fff · chore(gallery): fixup wan · Updated 2026-04-19 21:31:22 +00:00

371
0
Included

44e7d9806b · fix(distributed): stop queue loops on agent nodes + dead-letter cap · Updated 2026-04-19 21:27:05 +00:00

376
8

fbc93b0a34 · fix(llama-cpp): default rms_norm_eps for Gemma 3 GGUFs missing the key · Updated 2026-04-19 16:15:26 +00:00

374
1

cd56a05c3e · ci(vllm): disable tests-vllm-grpc job (heterogeneous runners) · Updated 2026-04-13 07:46:57 +00:00    Elgato_dark

441
16

5fe87cb0d5 · feat: upgrade banner with Upgrade All button, detect pre-existing backends · Updated 2026-04-11 22:11:23 +00:00    Elgato_dark

450
8

6e11f882f7 · feat(turboquant.cpp): add new backend · Updated 2026-04-03 20:57:15 +00:00    Elgato_dark

515
1

659636195c · deterministic builds · Updated 2026-04-01 19:45:31 +00:00    Elgato_dark

525
3