LocalAI/core/backend/token_metrics.go
LocalAI [bot] 2be07f61da
Some checks are pending
build backend container images / backend-jobs (insightface, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-insightface, 2404) (push) Waiting to run
build backend container images / backend-jobs (insightface, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-insightface, 2404) (push) Waiting to run
build backend container images / backend-jobs (kitten-tts, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -kitten-tts, 2404) (push) Waiting to run
build backend container images / backend-jobs (kokoro, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, intel, ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-kokoro, 2404) (push) Waiting to run
build backend container images / backend-jobs (kokoro, nvcr.io/nvidia/l4t-jetpack:r36.4.0, l4t, ./, 12, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, true, auto, -nvidia-l4t-kokoro, 2204) (push) Waiting to run
build backend container images / backend-jobs (kokoro, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-rocm-hipblas-kokoro, 2404) (push) Waiting to run
build backend container images / backend-jobs (kokoro, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-kokoro, 2404) (push) Waiting to run
build backend container images / backend-jobs (kokoro, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-kokoro, 2404) (push) Waiting to run
build backend container images / backend-jobs (kokoros, ubuntu:24.04, , ./, , , ./backend/Dockerfile.rust, linux/amd64, ubuntu-latest, false, auto, -cpu-kokoros, 2404) (push) Waiting to run
build backend container images / backend-jobs (llama-cpp, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, sycl_f16, ./, , , ./backend/Dockerfile.llama-cpp, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-sycl-f16-llama-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (llama-cpp, intel/oneapi-basekit:2025.3.2-0-devel-ubuntu24.04, sycl_f32, ./, , , ./backend/Dockerfile.llama-cpp, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-sycl-f32-llama-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (llama-cpp, nvcr.io/nvidia/l4t-jetpack:r36.4.0, cublas, ./, 12, 0, ./backend/Dockerfile.llama-cpp, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-arm64-llama-cpp, 2204) (push) Waiting to run
build backend container images / backend-jobs (llama-cpp, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.llama-cpp, linux/amd64, ubuntu-latest, false, auto, -gpu-rocm-hipblas-llama-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (llama-cpp, ubuntu:24.04, , ./, , , ./backend/Dockerfile.llama-cpp, linux/amd64,linux/arm64, bigger-runner, false, auto, -cpu-llama-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (llama-cpp, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.llama-cpp, linux/amd64, bigger-runner, false, auto, -gpu-nvidia-cuda-12-llama-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (llama-cpp, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.llama-cpp, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-llama-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (llama-cpp, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.llama-cpp, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-llama-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (llama-cpp, ubuntu:24.04, vulkan, ./, , , ./backend/Dockerfile.llama-cpp, linux/amd64,linux/arm64, bigger-runner, false, auto, -gpu-vulkan-llama-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (llama-cpp-quantization, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64,linux/arm64, ubuntu-latest, true, auto, -cpu-llama-cpp-quantization, 2404) (push) Waiting to run
build backend container images / backend-jobs (local-store, ubuntu:24.04, , ./, , , ./backend/Dockerfile.golang, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-local-store, 2404) (push) Waiting to run
build backend container images / backend-jobs (localvqe, ubuntu:24.04, , ./, , , ./backend/Dockerfile.golang, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-localvqe, 2404) (push) Waiting to run
build backend container images / backend-jobs (localvqe, ubuntu:24.04, vulkan, ./, , , ./backend/Dockerfile.golang, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -gpu-vulkan-localvqe, 2404) (push) Waiting to run
build backend container images / backend-jobs (mlx, nvcr.io/nvidia/l4t-jetpack:r36.4.0, l4t, ./, 12, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, true, auto, -nvidia-l4t-mlx, 2204) (push) Waiting to run
build backend container images / backend-jobs (mlx, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, true, auto, -cpu-mlx, 2404) (push) Waiting to run
build backend container images / backend-jobs (mlx, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-mlx, 2404) (push) Waiting to run
build backend container images / backend-jobs (mlx, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-mlx, 2404) (push) Waiting to run
build backend container images / backend-jobs (mlx, ubuntu:24.04, l4t, ./, 13, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-mlx, 2404) (push) Waiting to run
build backend container images / backend-jobs (mlx-audio, nvcr.io/nvidia/l4t-jetpack:r36.4.0, l4t, ./, 12, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, true, auto, -nvidia-l4t-mlx-audio, 2204) (push) Waiting to run
build backend container images / backend-jobs (mlx-audio, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, true, auto, -cpu-mlx-audio, 2404) (push) Waiting to run
build backend container images / backend-jobs (mlx-audio, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-mlx-audio, 2404) (push) Waiting to run
build backend container images / backend-jobs (mlx-audio, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-mlx-audio, 2404) (push) Waiting to run
build backend container images / backend-jobs (mlx-audio, ubuntu:24.04, l4t, ./, 13, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-mlx-audio, 2404) (push) Waiting to run
build backend container images / backend-jobs (mlx-distributed, nvcr.io/nvidia/l4t-jetpack:r36.4.0, l4t, ./, 12, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, true, auto, -nvidia-l4t-mlx-distributed, 2204) (push) Waiting to run
build backend container images / backend-jobs (mlx-distributed, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, true, auto, -cpu-mlx-distributed, 2404) (push) Waiting to run
build backend container images / backend-jobs (mlx-distributed, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-mlx-distributed, 2404) (push) Waiting to run
build backend container images / backend-jobs (mlx-distributed, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-mlx-distributed, 2404) (push) Waiting to run
build backend container images / backend-jobs (mlx-distributed, ubuntu:24.04, l4t, ./, 13, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-mlx-distributed, 2404) (push) Waiting to run
build backend container images / backend-jobs (mlx-vlm, nvcr.io/nvidia/l4t-jetpack:r36.4.0, l4t, ./, 12, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, true, auto, -nvidia-l4t-mlx-vlm, 2204) (push) Waiting to run
build backend container images / backend-jobs (mlx-vlm, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, true, auto, -cpu-mlx-vlm, 2404) (push) Waiting to run
build backend container images / backend-jobs (mlx-vlm, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-mlx-vlm, 2404) (push) Waiting to run
build backend container images / backend-jobs (mlx-vlm, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-mlx-vlm, 2404) (push) Waiting to run
build backend container images / backend-jobs (mlx-vlm, ubuntu:24.04, l4t, ./, 13, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-mlx-vlm, 2404) (push) Waiting to run
build backend container images / backend-jobs (moonshine, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, true, auto, -cpu-moonshine, 2404) (push) Waiting to run
build backend container images / backend-jobs (moonshine, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-moonshine, 2404) (push) Waiting to run
build backend container images / backend-jobs (moonshine, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-moonshine, 2404) (push) Waiting to run
build backend container images / backend-jobs (nemo, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, intel, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-intel-nemo, 2404) (push) Waiting to run
build backend container images / backend-jobs (nemo, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-rocm-hipblas-nemo, 2404) (push) Waiting to run
build backend container images / backend-jobs (nemo, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-nemo, 2404) (push) Waiting to run
build backend container images / backend-jobs (nemo, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-nemo, 2404) (push) Waiting to run
build backend container images / backend-jobs (nemo, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-nemo, 2404) (push) Waiting to run
build backend container images / backend-jobs (neutts, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-rocm-hipblas-neutts, 2404) (push) Waiting to run
build backend container images / backend-jobs (neutts, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-neutts, 2404) (push) Waiting to run
build backend container images / backend-jobs (neutts, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-neutts, 2404) (push) Waiting to run
build backend container images / backend-jobs (opus, ubuntu:24.04, , ./, , , ./backend/Dockerfile.golang, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-opus, 2404) (push) Waiting to run
build backend container images / backend-jobs (outetts, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, true, auto, -cpu-outetts, 2404) (push) Waiting to run
build backend container images / backend-jobs (outetts, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-outetts, 2404) (push) Waiting to run
build backend container images / backend-jobs (piper, ubuntu:24.04, , ./, , , ./backend/Dockerfile.golang, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -piper, 2404) (push) Waiting to run
build backend container images / backend-jobs (pocket-tts, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, intel, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-intel-pocket-tts, 2404) (push) Waiting to run
build backend container images / backend-jobs (pocket-tts, nvcr.io/nvidia/l4t-jetpack:r36.4.0, l4t, ./, 12, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, true, auto, -nvidia-l4t-pocket-tts, 2204) (push) Waiting to run
build backend container images / backend-jobs (pocket-tts, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-rocm-hipblas-pocket-tts, 2404) (push) Waiting to run
build backend container images / backend-jobs (pocket-tts, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-pocket-tts, 2404) (push) Waiting to run
build backend container images / backend-jobs (pocket-tts, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-pocket-tts, 2404) (push) Waiting to run
build backend container images / backend-jobs (pocket-tts, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-pocket-tts, 2404) (push) Waiting to run
build backend container images / backend-jobs (pocket-tts, ubuntu:24.04, l4t, ./, 13, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-pocket-tts, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen-asr, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, intel, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-intel-qwen-asr, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen-asr, nvcr.io/nvidia/l4t-jetpack:r36.4.0, l4t, ./, 12, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, true, auto, -nvidia-l4t-qwen-asr, 2204) (push) Waiting to run
build backend container images / backend-jobs (qwen-asr, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-rocm-hipblas-qwen-asr, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen-asr, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-qwen-asr, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen-asr, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-qwen-asr, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen-asr, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-qwen-asr, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen-asr, ubuntu:24.04, l4t, ./, 13, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-qwen-asr, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen-tts, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, intel, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-intel-qwen-tts, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen-tts, nvcr.io/nvidia/l4t-jetpack:r36.4.0, l4t, ./, 12, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, true, auto, -nvidia-l4t-qwen-tts, 2204) (push) Waiting to run
build backend container images / backend-jobs (qwen-tts, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-rocm-hipblas-qwen-tts, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen-tts, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-qwen-tts, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen-tts, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-qwen-tts, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen-tts, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-qwen-tts, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen-tts, ubuntu:24.04, l4t, ./, 13, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-qwen-tts, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen3-tts-cpp, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, sycl_f16, ./, , , ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-sycl-f16-qwen3-tts-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen3-tts-cpp, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, sycl_f32, ./, , , ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-sycl-f32-qwen3-tts-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen3-tts-cpp, nvcr.io/nvidia/l4t-jetpack:r36.4.0, cublas, ./, 12, 0, ./backend/Dockerfile.golang, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-arm64-qwen3-tts-cpp, 2204) (push) Waiting to run
build backend container images / backend-jobs (qwen3-tts-cpp, rocm/dev-ubuntu-24.04:6.4.4, hipblas, ./, , , ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-rocm-hipblas-qwen3-tts-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen3-tts-cpp, ubuntu:24.04, , ./, , , ./backend/Dockerfile.golang, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-qwen3-tts-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen3-tts-cpp, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-qwen3-tts-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen3-tts-cpp, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-qwen3-tts-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen3-tts-cpp, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.golang, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-qwen3-tts-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (qwen3-tts-cpp, ubuntu:24.04, vulkan, ./, , , ./backend/Dockerfile.golang, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -gpu-vulkan-qwen3-tts-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (rerankers, intel/oneapi-basekit:2025.3.2-0-devel-ubuntu24.04, intel, ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-rerankers, 2404) (push) Waiting to run
Tests extras backends / tests-ik-llama-cpp-grpc (push) Blocked by required conditions
build backend container images / backend-jobs (ace-step, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, intel, ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-ace-step, 2404) (push) Waiting to run
build backend container images / backend-jobs-darwin (qwen-tts, mps, -metal-darwin-arm64-qwen-tts) (push) Waiting to run
build backend container images / backend-jobs (rerankers, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-rocm-hipblas-rerankers, 2404) (push) Waiting to run
build backend container images / backend-jobs (diffusers, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, intel, ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-diffusers, 2404) (push) Waiting to run
build backend container images / backend-jobs (diffusers, nvcr.io/nvidia/l4t-jetpack:r36.4.0, l4t, ./, 12, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, true, auto, -nvidia-l4t-diffusers, 2204) (push) Waiting to run
build backend container images / backend-jobs (diffusers, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-rocm-hipblas-diffusers, 2404) (push) Waiting to run
build backend container images / backend-jobs (diffusers, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, true, auto, -cpu-diffusers, 2404) (push) Waiting to run
build backend container images / backend-jobs (diffusers, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-diffusers, 2404) (push) Waiting to run
build backend container images / backend-jobs (diffusers, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-diffusers, 2404) (push) Waiting to run
build backend container images / backend-jobs (ace-step, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-rocm-hipblas-ace-step, 2404) (push) Waiting to run
build backend container images / backend-jobs (ace-step, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, true, auto, -cpu-ace-step, 2404) (push) Waiting to run
build backend container images / backend-jobs (ace-step, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-ace-step, 2404) (push) Waiting to run
build backend container images / backend-jobs (ace-step, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-ace-step, 2404) (push) Waiting to run
build backend container images / backend-jobs (acestep-cpp, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, sycl_f16, ./, , , ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-sycl-f16-acestep-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (acestep-cpp, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, sycl_f32, ./, , , ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-sycl-f32-acestep-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (acestep-cpp, nvcr.io/nvidia/l4t-jetpack:r36.4.0, cublas, ./, 12, 0, ./backend/Dockerfile.golang, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-arm64-acestep-cpp, 2204) (push) Waiting to run
build backend container images / backend-jobs (acestep-cpp, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-rocm-hipblas-acestep-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (acestep-cpp, ubuntu:24.04, , ./, , , ./backend/Dockerfile.golang, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-acestep-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (acestep-cpp, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-acestep-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (acestep-cpp, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-acestep-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (acestep-cpp, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.golang, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-acestep-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (acestep-cpp, ubuntu:24.04, vulkan, ./, , , ./backend/Dockerfile.golang, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -gpu-vulkan-acestep-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (chatterbox, nvcr.io/nvidia/l4t-jetpack:r36.4.0, l4t, ./, 12, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, true, auto, -nvidia-l4t-arm64-chatterbox, 2204) (push) Waiting to run
build backend container images / backend-jobs (chatterbox, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, true, auto, -cpu-chatterbox, 2404) (push) Waiting to run
build backend container images / backend-jobs (chatterbox, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-chatterbox, 2404) (push) Waiting to run
build backend container images / backend-jobs (chatterbox, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-chatterbox, 2404) (push) Waiting to run
build backend container images / backend-jobs (chatterbox, ubuntu:24.04, l4t, ./, 13, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-chatterbox, 2404) (push) Waiting to run
build backend container images / backend-jobs (coqui, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, intel, ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-coqui, 2404) (push) Waiting to run
build backend container images / backend-jobs (coqui, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.python, linux/amd64, bigger-runner, false, auto, -gpu-rocm-hipblas-coqui, 2404) (push) Waiting to run
build backend container images / backend-jobs (coqui, ubuntu:24.04, cublas, ./, 12, 9, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-coqui, 2404) (push) Waiting to run
build backend container images / backend-jobs (rerankers, ubuntu:24.04, cublas, ./, 12, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-rerankers, 2404) (push) Waiting to run
build backend container images / backend-jobs (rerankers, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-rerankers, 2404) (push) Waiting to run
build backend container images / backend-jobs (rfdetr, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, intel, ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-rfdetr, 2404) (push) Waiting to run
build backend container images / backend-jobs (rfdetr, nvcr.io/nvidia/l4t-jetpack:r36.4.0, l4t, ./, 12, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, true, auto, -nvidia-l4t-arm64-rfdetr, 2204) (push) Waiting to run
build backend container images / backend-jobs (rfdetr, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-rfdetr, 2404) (push) Waiting to run
build backend container images / backend-jobs (rfdetr, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-rfdetr, 2404) (push) Waiting to run
build backend container images / backend-jobs-darwin (qwen3-tts-cpp, metal, go, -metal-darwin-arm64-qwen3-tts-cpp) (push) Waiting to run
build backend container images / backend-jobs (diffusers, ubuntu:24.04, l4t, ./, 13, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-diffusers, 2404) (push) Waiting to run
build backend container images / backend-jobs (faster-qwen3-tts, nvcr.io/nvidia/l4t-jetpack:r36.4.0, l4t, ./, 12, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, true, auto, -nvidia-l4t-faster-qwen3-tts, 2204) (push) Waiting to run
build backend container images / backend-jobs (faster-qwen3-tts, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-faster-qwen3-tts, 2404) (push) Waiting to run
build backend container images / backend-jobs (faster-qwen3-tts, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-faster-qwen3-tts, 2404) (push) Waiting to run
build backend container images / backend-jobs (faster-qwen3-tts, ubuntu:24.04, l4t, ./, 13, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-faster-qwen3-tts, 2404) (push) Waiting to run
build backend container images / backend-jobs (faster-whisper, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, intel, ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-faster-whisper, 2404) (push) Waiting to run
build backend container images / backend-jobs (faster-whisper, nvcr.io/nvidia/l4t-jetpack:r36.4.0, l4t, ./, 12, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, true, auto, -nvidia-l4t-faster-whisper, 2204) (push) Waiting to run
build backend container images / backend-jobs (faster-whisper, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.python, linux/amd64, bigger-runner, false, auto, -gpu-rocm-hipblas-faster-whisper, 2404) (push) Waiting to run
build backend container images / backend-jobs (faster-whisper, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64,linux/arm64, ubuntu-latest, true, auto, -cpu-faster-whisper, 2404) (push) Waiting to run
build backend container images / backend-jobs (faster-whisper, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-faster-whisper, 2404) (push) Waiting to run
build backend container images / backend-jobs (faster-whisper, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-faster-whisper, 2404) (push) Waiting to run
build backend container images / backend-jobs (faster-whisper, ubuntu:24.04, l4t, ./, 13, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-faster-whisper, 2404) (push) Waiting to run
build backend container images / backend-jobs (fish-speech, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, intel, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-intel-fish-speech, 2404) (push) Waiting to run
build backend container images / backend-jobs (fish-speech, nvcr.io/nvidia/l4t-jetpack:r36.4.0, l4t, ./, 12, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, true, auto, -nvidia-l4t-fish-speech, 2204) (push) Waiting to run
build backend container images / backend-jobs (fish-speech, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-rocm-hipblas-fish-speech, 2404) (push) Waiting to run
build backend container images / backend-jobs (fish-speech, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-fish-speech, 2404) (push) Waiting to run
build backend container images / backend-jobs (fish-speech, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-fish-speech, 2404) (push) Waiting to run
build backend container images / backend-jobs (fish-speech, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-fish-speech, 2404) (push) Waiting to run
build backend container images / backend-jobs (fish-speech, ubuntu:24.04, l4t, ./, 13, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-fish-speech, 2404) (push) Waiting to run
build backend container images / backend-jobs (ik-llama-cpp, ubuntu:24.04, , ./, , , ./backend/Dockerfile.ik-llama-cpp, linux/amd64, bigger-runner, false, auto, -cpu-ik-llama-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (rfdetr, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-rfdetr, 2404) (push) Waiting to run
build backend container images / backend-jobs (sam3-cpp, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, sycl_f16, ./, , , ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-sycl-f16-sam3-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (sam3-cpp, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, sycl_f32, ./, , , ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-sycl-f32-sam3-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (sam3-cpp, nvcr.io/nvidia/l4t-jetpack:r36.4.0, cublas, ./, 12, 0, ./backend/Dockerfile.golang, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-arm64-sam3-cpp, 2204) (push) Waiting to run
build backend container images / backend-jobs (sam3-cpp, ubuntu:24.04, , ./, , , ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -cpu-sam3-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (sam3-cpp, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-sam3-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (sam3-cpp, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-sam3-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (sam3-cpp, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.golang, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-sam3-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (sam3-cpp, ubuntu:24.04, vulkan, ./, , , ./backend/Dockerfile.golang, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -gpu-vulkan-sam3-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (sglang, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, intel, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-intel-sglang, 2404) (push) Waiting to run
build backend container images / backend-jobs (sglang, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-rocm-hipblas-sglang, 2404) (push) Waiting to run
build backend container images / backend-jobs (sglang, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, true, auto, -cpu-sglang, 2404) (push) Waiting to run
build backend container images / backend-jobs (sglang, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-nvidia-cuda-12-sglang, 2404) (push) Waiting to run
build backend container images / backend-jobs (sglang, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-nvidia-cuda-13-sglang, 2404) (push) Waiting to run
build backend container images / backend-jobs (sglang, ubuntu:24.04, l4t, ./, 13, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-sglang, 2404) (push) Waiting to run
build backend container images / backend-jobs (sherpa-onnx, ubuntu:24.04, , ./, , , ./backend/Dockerfile.golang, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-sherpa-onnx, 2404) (push) Waiting to run
build backend container images / backend-jobs (sherpa-onnx, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-sherpa-onnx, 2404) (push) Waiting to run
build backend container images / backend-jobs (sherpa-onnx, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-sherpa-onnx, 2404) (push) Waiting to run
build backend container images / backend-jobs (silero-vad, ubuntu:24.04, , ./, , , ./backend/Dockerfile.golang, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-silero-vad, 2404) (push) Waiting to run
build backend container images / backend-jobs (speaker-recognition, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-speaker-recognition, 2404) (push) Waiting to run
build backend container images / backend-jobs (speaker-recognition, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-speaker-recognition, 2404) (push) Waiting to run
build backend container images / backend-jobs (stablediffusion-ggml, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, sycl_f16, ./, , , ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-sycl-f16-stablediffusion-ggml, 2404) (push) Waiting to run
build backend container images / backend-jobs (stablediffusion-ggml, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, sycl_f32, ./, , , ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-sycl-f32-stablediffusion-ggml, 2404) (push) Waiting to run
build backend container images / backend-jobs (stablediffusion-ggml, nvcr.io/nvidia/l4t-jetpack:r36.4.0, cublas, ./, 12, 0, ./backend/Dockerfile.golang, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-arm64-stablediffusion-ggml, 2204) (push) Waiting to run
build backend container images / backend-jobs (stablediffusion-ggml, ubuntu:24.04, , ./, , , ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -cpu-stablediffusion-ggml, 2404) (push) Waiting to run
build backend container images / backend-jobs (stablediffusion-ggml, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-stablediffusion-ggml, 2404) (push) Waiting to run
build backend container images / backend-jobs (stablediffusion-ggml, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-stablediffusion-ggml, 2404) (push) Waiting to run
build backend container images / backend-jobs (stablediffusion-ggml, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.golang, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-stablediffusion-ggml, 2404) (push) Waiting to run
build backend container images / backend-jobs (stablediffusion-ggml, ubuntu:24.04, vulkan, ./, , , ./backend/Dockerfile.golang, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -gpu-vulkan-stablediffusion-ggml, 2404) (push) Waiting to run
build backend container images / backend-jobs (tinygrad, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, true, auto, -tinygrad, 2404) (push) Waiting to run
build backend container images / backend-jobs (transformers, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, intel, ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-transformers, 2404) (push) Waiting to run
build backend container images / backend-jobs (transformers, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-rocm-hipblas-transformers, 2404) (push) Waiting to run
build backend container images / backend-jobs (transformers, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-transformers, 2404) (push) Waiting to run
build backend container images / backend-jobs (transformers, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-transformers, 2404) (push) Waiting to run
build backend container images / backend-jobs (trl, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, true, auto, -cpu-trl, 2404) (push) Waiting to run
build backend container images / backend-jobs (trl, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-trl, 2404) (push) Waiting to run
build backend container images / backend-jobs (trl, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-trl, 2404) (push) Waiting to run
build backend container images / backend-jobs (turboquant, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, sycl_f16, ./, , , ./backend/Dockerfile.turboquant, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-sycl-f16-turboquant, 2404) (push) Waiting to run
build backend container images / backend-jobs (turboquant, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, sycl_f32, ./, , , ./backend/Dockerfile.turboquant, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-sycl-f32-turboquant, 2404) (push) Waiting to run
build backend container images / backend-jobs (turboquant, nvcr.io/nvidia/l4t-jetpack:r36.4.0, cublas, ./, 12, 0, ./backend/Dockerfile.turboquant, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-arm64-turboquant, 2204) (push) Waiting to run
build backend container images / backend-jobs (turboquant, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.turboquant, linux/amd64, ubuntu-latest, false, auto, -gpu-rocm-hipblas-turboquant, 2404) (push) Waiting to run
build backend container images / backend-jobs (turboquant, ubuntu:24.04, , ./, , , ./backend/Dockerfile.turboquant, linux/amd64,linux/arm64, bigger-runner, false, auto, -cpu-turboquant, 2404) (push) Waiting to run
build backend container images / backend-jobs (turboquant, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.turboquant, linux/amd64, bigger-runner, false, auto, -gpu-nvidia-cuda-12-turboquant, 2404) (push) Waiting to run
build backend container images / backend-jobs (turboquant, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.turboquant, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-turboquant, 2404) (push) Waiting to run
build backend container images / backend-jobs (turboquant, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.turboquant, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-turboquant, 2404) (push) Waiting to run
build backend container images / backend-jobs (turboquant, ubuntu:24.04, vulkan, ./, , , ./backend/Dockerfile.turboquant, linux/amd64,linux/arm64, bigger-runner, false, auto, -gpu-vulkan-turboquant, 2404) (push) Waiting to run
build backend container images / backend-jobs (vibevoice, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, intel, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-intel-vibevoice, 2404) (push) Waiting to run
build backend container images / backend-jobs (vibevoice, nvcr.io/nvidia/l4t-jetpack:r36.4.0, l4t, ./, 12, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, true, auto, -nvidia-l4t-vibevoice, 2204) (push) Waiting to run
build backend container images / backend-jobs (vibevoice, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-rocm-hipblas-vibevoice, 2404) (push) Waiting to run
build backend container images / backend-jobs (vibevoice, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-vibevoice, 2404) (push) Waiting to run
build backend container images / backend-jobs (vibevoice, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-vibevoice, 2404) (push) Waiting to run
build backend container images / backend-jobs (vibevoice, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-vibevoice, 2404) (push) Waiting to run
build backend container images / backend-jobs (vibevoice, ubuntu:24.04, l4t, ./, 13, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-vibevoice, 2404) (push) Waiting to run
build backend container images / backend-jobs (vibevoice-cpp, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, sycl_f16, ./, , , ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-sycl-f16-vibevoice-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (vibevoice-cpp, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, sycl_f32, ./, , , ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-sycl-f32-vibevoice-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (vibevoice-cpp, nvcr.io/nvidia/l4t-jetpack:r36.4.0, cublas, ./, 12, 0, ./backend/Dockerfile.golang, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-arm64-vibevoice-cpp, 2204) (push) Waiting to run
build backend container images / backend-jobs (vibevoice-cpp, rocm/dev-ubuntu-24.04:6.4.4, hipblas, ./, , , ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-rocm-hipblas-vibevoice-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (vibevoice-cpp, ubuntu:24.04, , ./, , , ./backend/Dockerfile.golang, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-vibevoice-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (vibevoice-cpp, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-vibevoice-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (vibevoice-cpp, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-vibevoice-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (vibevoice-cpp, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.golang, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-vibevoice-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (vibevoice-cpp, ubuntu:24.04, vulkan, ./, , , ./backend/Dockerfile.golang, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -gpu-vulkan-vibevoice-cpp, 2404) (push) Waiting to run
build backend container images / backend-jobs (vllm, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, intel, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-intel-vllm, 2404) (push) Waiting to run
build backend container images / backend-jobs (vllm, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-rocm-hipblas-vllm, 2404) (push) Waiting to run
build backend container images / backend-jobs (vllm, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, true, auto, -cpu-vllm, 2404) (push) Waiting to run
build backend container images / backend-jobs (vllm, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-nvidia-cuda-12-vllm, 2404) (push) Waiting to run
build backend container images / backend-jobs (vllm, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-nvidia-cuda-13-vllm, 2404) (push) Waiting to run
build backend container images / backend-jobs (vllm, ubuntu:24.04, l4t, ./, 13, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-vllm, 2404) (push) Waiting to run
build backend container images / backend-jobs (vllm-omni, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-rocm-hipblas-vllm-omni, 2404) (push) Waiting to run
build backend container images / backend-jobs (vllm-omni, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-nvidia-cuda-12-vllm-omni, 2404) (push) Waiting to run
build backend container images / backend-jobs (vllm-omni, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-nvidia-cuda-13-vllm-omni, 2404) (push) Waiting to run
build backend container images / backend-jobs (vllm-omni, ubuntu:24.04, l4t, ./, 13, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-vllm-omni, 2404) (push) Waiting to run
build backend container images / backend-jobs (voxcpm, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, intel, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-intel-voxcpm, 2404) (push) Waiting to run
build backend container images / backend-jobs (voxcpm, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.python, linux/amd64, arc-runner-set, false, auto, -gpu-rocm-hipblas-voxcpm, 2404) (push) Waiting to run
build backend container images / backend-jobs (voxcpm, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -cpu-voxcpm, 2404) (push) Waiting to run
build backend container images / backend-jobs (voxcpm, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-voxcpm, 2404) (push) Waiting to run
build backend container images / backend-jobs (voxcpm, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-voxcpm, 2404) (push) Waiting to run
build backend container images / backend-jobs (voxtral, ubuntu:24.04, , ./, , , ./backend/Dockerfile.golang, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-voxtral, 2404) (push) Waiting to run
build backend container images / backend-jobs (whisper, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, sycl_f16, ./, , , ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-sycl-f16-whisper, 2404) (push) Waiting to run
build backend container images / backend-jobs (whisper, intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04, sycl_f32, ./, , , ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-intel-sycl-f32-whisper, 2404) (push) Waiting to run
build backend container images / backend-jobs (whisper, nvcr.io/nvidia/l4t-jetpack:r36.4.0, cublas, ./, 12, 0, ./backend/Dockerfile.golang, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-arm64-whisper, 2204) (push) Waiting to run
build backend container images / backend-jobs (whisper, rocm/dev-ubuntu-24.04:7.2.1, hipblas, ./, , , ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-rocm-hipblas-whisper, 2404) (push) Waiting to run
build backend container images / backend-jobs (whisper, ubuntu:24.04, , ./, , , ./backend/Dockerfile.golang, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -cpu-whisper, 2404) (push) Waiting to run
build backend container images / backend-jobs (whisper, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-whisper, 2404) (push) Waiting to run
build backend container images / backend-jobs (whisper, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.golang, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-whisper, 2404) (push) Waiting to run
build backend container images / backend-jobs (whisper, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.golang, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-whisper, 2404) (push) Waiting to run
build backend container images / backend-jobs (whisper, ubuntu:24.04, vulkan, ./, , , ./backend/Dockerfile.golang, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -gpu-vulkan-whisper, 2404) (push) Waiting to run
build backend container images / backend-jobs (whisperx, nvcr.io/nvidia/l4t-jetpack:r36.4.0, l4t, ./, 12, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, true, auto, -nvidia-l4t-whisperx, 2204) (push) Waiting to run
build backend container images / backend-jobs (whisperx, ubuntu:24.04, , ./, , , ./backend/Dockerfile.python, linux/amd64,linux/arm64, ubuntu-latest, true, auto, -cpu-whisperx, 2404) (push) Waiting to run
build backend container images / backend-jobs (whisperx, ubuntu:24.04, cublas, ./, 12, 8, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-12-whisperx, 2404) (push) Waiting to run
build backend container images / backend-jobs (whisperx, ubuntu:24.04, cublas, ./, 13, 0, ./backend/Dockerfile.python, linux/amd64, ubuntu-latest, false, auto, -gpu-nvidia-cuda-13-whisperx, 2404) (push) Waiting to run
build backend container images / backend-jobs (whisperx, ubuntu:24.04, l4t, ./, 13, 0, ./backend/Dockerfile.python, linux/arm64, ubuntu-24.04-arm, false, auto, -nvidia-l4t-cuda-13-arm64-whisperx, 2404) (push) Waiting to run
build backend container images / backend-jobs-darwin (ace-step, mps, -metal-darwin-arm64-ace-step) (push) Waiting to run
build backend container images / backend-jobs-darwin (acestep-cpp, metal, go, -metal-darwin-arm64-acestep-cpp) (push) Waiting to run
build backend container images / backend-jobs-darwin (chatterbox, mps, -metal-darwin-arm64-chatterbox) (push) Waiting to run
build backend container images / backend-jobs-darwin (coqui, mps, -metal-darwin-arm64-coqui) (push) Waiting to run
build backend container images / backend-jobs-darwin (diffusers, mps, -metal-darwin-arm64-diffusers) (push) Waiting to run
build backend container images / backend-jobs-darwin (faster-whisper, mps, -metal-darwin-arm64-faster-whisper) (push) Waiting to run
build backend container images / backend-jobs-darwin (fish-speech, mps, -metal-darwin-arm64-fish-speech) (push) Waiting to run
build backend container images / backend-jobs-darwin (kitten-tts, mps, -metal-darwin-arm64-kitten-tts) (push) Waiting to run
build backend container images / backend-jobs-darwin (kokoro, mps, -metal-darwin-arm64-kokoro) (push) Waiting to run
build backend container images / backend-jobs-darwin (llama-cpp-quantization, mps, -metal-darwin-arm64-llama-cpp-quantization) (push) Waiting to run
build backend container images / backend-jobs-darwin (local-store, metal, go, -metal-darwin-arm64-local-store) (push) Waiting to run
build backend container images / backend-jobs-darwin (mlx, mps, -metal-darwin-arm64-mlx) (push) Waiting to run
build backend container images / backend-jobs-darwin (mlx-audio, mps, -metal-darwin-arm64-mlx-audio) (push) Waiting to run
build backend container images / backend-jobs-darwin (mlx-distributed, mps, -metal-darwin-arm64-mlx-distributed) (push) Waiting to run
build backend container images / backend-jobs-darwin (mlx-vlm, mps, -metal-darwin-arm64-mlx-vlm) (push) Waiting to run
build backend container images / backend-jobs-darwin (moonshine, mps, -metal-darwin-arm64-moonshine) (push) Waiting to run
build backend container images / backend-jobs-darwin (nemo, mps, -metal-darwin-arm64-nemo) (push) Waiting to run
build backend container images / backend-jobs-darwin (opus, metal, go, -metal-darwin-arm64-opus) (push) Waiting to run
build backend container images / backend-jobs-darwin (piper, metal, go, -metal-darwin-arm64-piper) (push) Waiting to run
build backend container images / backend-jobs-darwin (pocket-tts, mps, -metal-darwin-arm64-pocket-tts) (push) Waiting to run
build backend container images / backend-jobs-darwin (qwen-asr, mps, -metal-darwin-arm64-qwen-asr) (push) Waiting to run
build backend container images / backend-jobs-darwin (rerankers, mps, -metal-darwin-arm64-rerankers) (push) Waiting to run
build backend container images / backend-jobs-darwin (rfdetr, mps, -metal-darwin-arm64-rfdetr) (push) Waiting to run
build backend container images / backend-jobs-darwin (silero-vad, metal, go, -metal-darwin-arm64-silero-vad) (push) Waiting to run
build backend container images / backend-jobs-darwin (stablediffusion-ggml, metal, go, -metal-darwin-arm64-stablediffusion-ggml) (push) Waiting to run
build backend container images / backend-jobs-darwin (transformers, mps, -metal-darwin-arm64-transformers) (push) Waiting to run
build backend container images / backend-jobs-darwin (vibevoice, mps, -metal-darwin-arm64-vibevoice) (push) Waiting to run
build backend container images / backend-jobs-darwin (vibevoice-cpp, metal, go, -metal-darwin-arm64-vibevoice-cpp) (push) Waiting to run
build backend container images / backend-jobs-darwin (voxcpm, mps, -metal-darwin-arm64-voxcpm) (push) Waiting to run
build backend container images / backend-jobs-darwin (voxtral, metal, go, -metal-darwin-arm64-voxtral) (push) Waiting to run
build backend container images / backend-jobs-darwin (whisper, metal, go, -metal-darwin-arm64-whisper) (push) Waiting to run
build backend container images / backend-jobs-darwin (whisperx, mps, -metal-darwin-arm64-whisperx) (push) Waiting to run
build backend container images / llama-cpp-darwin (1.25.x) (push) Waiting to run
build backend container images / llama-cpp-darwin-publish (push) Blocked by required conditions
Build test / build-test (push) Waiting to run
Build test / launcher-build-darwin (push) Waiting to run
Build test / launcher-build-linux (push) Waiting to run
Explorer deployment / build-linux (push) Waiting to run
GPU tests / ubuntu-latest (1.21.x) (push) Waiting to run
generate and publish intel docker caches / generate_caches (intel/oneapi-basekit:2025.3.2-0-devel-ubuntu24.04, linux/amd64, arc-runner-set) (push) Waiting to run
Deploy docs to GitHub Pages / build (push) Waiting to run
Deploy docs to GitHub Pages / deploy (push) Blocked by required conditions
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) Waiting to run
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) Waiting to run
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) Waiting to run
build container images / core-image-build (ubuntu:24.04, , --jobs=4 --output-sync=target, linux/amd64,linux/arm64, ubuntu-latest, false, auto, , noble, 2404) (push) Waiting to run
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) Waiting to run
build container images / core-image-build (ubuntu:24.04, vulkan, --jobs=4 --output-sync=target, linux/amd64,linux/arm64, ubuntu-latest, false, auto, -gpu-vulkan, noble, 2404) (push) Waiting to run
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) Waiting to run
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) Waiting to run
lint / golangci-lint (push) Waiting to run
Security Scan / tests (push) Waiting to run
Tests extras backends / detect-changes (push) Waiting to run
Tests extras backends / tests-transformers (push) Blocked by required conditions
Tests extras backends / tests-rerankers (push) Blocked by required conditions
Tests extras backends / tests-diffusers (push) Blocked by required conditions
Tests extras backends / tests-coqui (push) Blocked by required conditions
Tests extras backends / tests-moonshine (push) Blocked by required conditions
Tests extras backends / tests-pocket-tts (push) Blocked by required conditions
Tests extras backends / tests-qwen-tts (push) Blocked by required conditions
Tests extras backends / tests-qwen-asr (push) Blocked by required conditions
Tests extras backends / tests-nemo (push) Blocked by required conditions
Tests extras backends / tests-voxcpm (push) Blocked by required conditions
Tests extras backends / tests-llama-cpp-quantization (push) Blocked by required conditions
Tests extras backends / tests-llama-cpp-grpc (push) Blocked by required conditions
Tests extras backends / tests-llama-cpp-grpc-transcription (push) Blocked by required conditions
Tests extras backends / tests-llama-cpp-smoke (push) Waiting to run
Tests extras backends / tests-sherpa-onnx-realtime (push) Blocked by required conditions
Tests extras backends / tests-sherpa-onnx-grpc-transcription (push) Blocked by required conditions
Tests extras backends / tests-sherpa-onnx-grpc-tts (push) Blocked by required conditions
Tests extras backends / tests-turboquant-grpc (push) Blocked by required conditions
Tests extras backends / tests-acestep-cpp (push) Blocked by required conditions
Tests extras backends / tests-qwen3-tts-cpp (push) Blocked by required conditions
Tests extras backends / tests-vibevoice-cpp (push) Blocked by required conditions
Tests extras backends / tests-vibevoice-cpp-grpc-tts (push) Blocked by required conditions
Tests extras backends / tests-vibevoice-cpp-grpc-transcription (push) Blocked by required conditions
Tests extras backends / tests-localvqe-grpc-transform (push) Blocked by required conditions
Tests extras backends / tests-voxtral (push) Blocked by required conditions
Tests extras backends / tests-kokoros (push) Blocked by required conditions
Tests extras backends / tests-insightface-grpc (push) Blocked by required conditions
Tests extras backends / tests-speaker-recognition-grpc (push) Blocked by required conditions
tests / tests-linux (1.26.x) (push) Waiting to run
tests / tests-apple (1.26.x) (push) Waiting to run
tests-aio / tests-aio (push) Waiting to run
E2E Backend Tests / tests-e2e-backend (1.25.x) (push) Waiting to run
UI E2E Tests / tests-ui-e2e (1.26.x) (push) Waiting to run
feat(whisper): honor client cancellation via ggml abort_callback (#9710)
* refactor(transcription): propagate request ctx through ModelTranscription*

Replaces context.Background() with the HTTP request ctx so client
disconnects start cancelling the gRPC call. No backend-side abort wiring
yet — that comes in a later commit. Pure plumbing.

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(cli): pass ctx to backend.ModelTranscription

Follow-up to e65d3e1f which threaded ctx through ModelTranscription
but missed the CLI caller. CLI commands have no request-scoped ctx,
so context.Background() is correct here.

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactor(audio): propagate request ctx into TTS, sound-gen, audio-transform

Same ctx-plumbing pattern applied to the rest of the audio path. CLI
callers use context.Background() since there is no request scope; HTTP
callers use c.Request().Context().

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactor(backend): propagate request ctx into biometric, detection, rerank, diarization paths

Replaces remaining context.Background() sites in core/backend with the
caller's ctx. After this commit, every core/backend/*.go entry point
threads the request ctx end-to-end to the gRPC client.

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactor(grpc): plumb ctx through AIModel.AudioTranscription{,Stream}

Adds context.Context as first parameter to the AIModel interface methods
that wrap whisper-style transcription. Server-side gRPC handler now
forwards the per-RPC ctx (server-streaming uses stream.Context()).
Whisper, Voxtral, vibevoice-cpp, and sherpa-onnx accept the parameter;
none uses it yet — the actual cancellation primitive lands in the next
commit so this is pure plumbing.

Assisted-by: Claude:claude-sonnet-4-6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(whisper): add abort_callback hook in the C++ bridge

Installs a std::atomic<int> flag, wires it into
whisper_full_params.abort_callback, and exposes a set_abort(int) C
symbol so Go can flip the flag from a goroutine watching the request
context. transcribe() now distinguishes abort (return 2) from real
whisper_full failure (return 1).

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(whisper): register set_abort symbol in the purego loader

Adds the Go-side binding for the new C export so the next commit can
call CppSetAbort(1) from a watcher goroutine on ctx.Done().

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(whisper): honor ctx cancellation and return codes.Canceled

A watcher goroutine watches ctx.Done() during AudioTranscription and
calls CppSetAbort(1) on cancel. whisper_full sees abort_callback return
true at the next compute graph step, returns non-zero, and the bridge
returns 2 -> AudioTranscription maps that to codes.Canceled.

Adds an opt-in test (gated on WHISPER_MODEL_PATH / WHISPER_AUDIO_PATH)
that asserts cancellation latency under 5s and proves the abort flag
resets cleanly so the next transcription succeeds.

Assisted-by: Claude:claude-sonnet-4-6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(whisper): join the cancel watcher goroutine before returning

Follow-up to 85edf9d2. The previous commit used `defer close(done)` and
called the watcher "joined synchronously" — but close() only signals,
it does not block until the goroutine exits. That left a window where
a late CppSetAbort(1) from a cancelled call could land on the next
call, after its C-side g_abort reset but before whisper_full() began
polling the abort callback, corrupting the second transcription.

Switch to a sync.WaitGroup join so wg.Wait() blocks until the watcher
has actually returned from its select.

Assisted-by: Claude:claude-sonnet-4-6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(whisper): short-circuit pre-cancelled ctx in AudioTranscription

If ctx is already Done() at entry, return codes.Canceled immediately
instead of running the full transcription. The C-side g_abort reset
happens at the start of transcribe() and would otherwise overwrite a
watcher-set abort flag from an already-cancelled ctx, producing a
spurious successful transcription on a request the client has already
abandoned.

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(tests/distributed): update testLLM mock for new AudioTranscription signature

Phase B (93c48e19) added context.Context to AIModel.AudioTranscription
but missed the testLLM mock in tests/e2e/distributed. CI golangci-lint
caught it: *testLLM did not implement grpc.AIModel because the method
signature lacked the ctx parameter, which broke the distributed test
suite compilation and cascaded through every backend-build job that
runs `go build ./...`.

Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* test(whisper): port cancellation test to Ginkgo/Gomega

Project policy (.agents/coding-style.md, enforced by golangci-lint
forbidigo) is that all Go tests must use Ginkgo v2 + Gomega — no
stdlib testing patterns (t.Skip, t.Fatalf, etc.). Convert the
cancellation test to a Describe/It block with Skip(...) for env
gating and Expect/HaveOccurred for assertions.

Same coverage: cancel mid-flight returns codes.Canceled within 5s and
a follow-up transcription succeeds, proving the C-side g_abort flag
resets cleanly.

Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
2026-05-08 01:44:47 +02:00

33 lines
768 B
Go

package backend
import (
"context"
"fmt"
"github.com/mudler/LocalAI/core/config"
"github.com/mudler/LocalAI/pkg/grpc/proto"
model "github.com/mudler/LocalAI/pkg/model"
)
func TokenMetrics(
ctx context.Context,
modelFile string,
loader *model.ModelLoader,
appConfig *config.ApplicationConfig,
modelConfig config.ModelConfig) (*proto.MetricsResponse, error) {
opts := ModelOptions(modelConfig, appConfig, model.WithModel(modelFile))
model, err := loader.Load(opts...)
if err != nil {
recordModelLoadFailure(appConfig, modelConfig.Name, modelConfig.Backend, err, nil)
return nil, err
}
if model == nil {
return nil, fmt.Errorf("could not loadmodel model")
}
res, err := model.GetTokenMetrics(ctx, &proto.MetricsRequest{})
return res, err
}