fix(darwin): publish sherpa-onnx and speaker-recognition images for darwin/arm64 - #10275
Merged
Conversation
…arwin/arm64 Neither the sherpa-onnx nor the speaker-recognition backend had a darwin/arm64 image, so `local-ai backends install` failed with "no child with platform darwin/arm64" on macOS. This left /v1/audio/diarization (the sherpa-onnx path) and /v1/voice/embed without any usable backend on Apple Silicon. Both backends build on darwin/arm64: - sherpa-onnx (Go) already fetches the onnxruntime osx-arm64 runtime in its Makefile; it only needed a darwin matrix entry (build-type metal, lang go, like whisper and silero-vad). - speaker-recognition (Python) needed a requirements-mps.txt so the mps build installs plain onnxruntime (which ships a macOS arm64 wheel) instead of the onnxruntime-gpu pulled by its base requirements (which does not). Add both to the includeDarwin build matrix, wire the metal capability and metal image aliases into the gallery, and add the speaker-recognition requirements-mps.txt. Fixes #10268 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code]
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Fixes #10268.
Neither the
sherpa-onnxnor thespeaker-recognitionbackend had a darwin/arm64 image, solocal-ai backends installfailed on macOS with:This left
/v1/audio/diarization(the sherpa-onnx path) and/v1/voice/embedwithout any usable backend on Apple Silicon.Change
Both backends build on darwin/arm64:
onnxruntime-osx-arm64runtime, so it only needed a darwin matrix entry (build-type: metal,lang: go, like whisper / silero-vad).requirements-mps.txtso thempsbuild installs plainonnxruntime(which ships a macOS arm64 wheel) instead of theonnxruntime-gpupulled by its base requirements (which does not).Specifically:
.github/backend-matrix.yml: add both toincludeDarwin.backend/index.yaml: add themetal:capability +metal-*image aliases (and-developmentvariants) for both, mirroringmetal-whisper.backend/python/speaker-recognition/requirements-mps.txt: new file.Verification
YAML parses for both files;
core/gallerytests pass. This is CI/build config — the real proof is a green darwin CI run, which I can't reproduce locally. sherpa-onnx is essentially pure CI wiring (native build already darwin-ready); speaker-recognition's only code artifact is the new requirements file.Assisted-by: Claude:claude-opus-4-8 [Claude Code]