0dbc0300d7
Some checks failed
Release / semantic-release (push) Successful in 19s
tests / Unit tests (Linux, Python 3.11) (push) Successful in 9m54s
Release / build-linux (push) Failing after 7m14s
Release / build-windows (push) Has been cancelled
Release / build-macos (arm64, macos-latest) (push) Has been cancelled
Release / build-macos (x64, macos-15-intel) (push) Has been cancelled
Release / release-main (push) Has been cancelled
Release / release-develop (push) Has been cancelled
GPU acceleration is now on by default and verified end-to-end on the Blackwell RTX 5050 (sm_120): - Ollama offloads 100% to GPU (log: library=CUDA compute=12.0, BLACKWELL_NATIVE_FP4=1). compose passes GPU via CDI (devices: nvidia.com/gpu=all) to both ollama and javis. - Whisper STT on GPU: faster-whisper>=1.1.0 + nvidia-cublas/cudnn cu12, LD_LIBRARY_PATH baked into the image. Verified float16 transcribe on sm_120; bridge auto-falls back to CPU when no GPU is present. - Model: default chat model -> qwen3:8b (best 8GB-VRAM tool-calling, ~5GB Q4). Embed stays nomic-embed-text. - README documents the host one-time setup (nvidia-container-toolkit + `nvidia-ctk cdi generate`) and GPU on/off. Verified: image builds; GPU visible in both containers via compose; ollama ps = 100% GPU; faster-whisper cuda OK + CPU fallback OK; bridge /health 200.
3.3 KiB
3.3 KiB