mirror of
https://github.com/mudler/LocalAI
synced 2026-05-24 09:28:23 +00:00
39573ecd2a
whisperx has no upstream AMD GPU support and its core transcription path (faster-whisper -> ctranslate2) falls back to CPU on AMD since the PyPI ctranslate2 is CUDA-only. The torch rocm wheels would accelerate only the alignment/diarization stages, producing a misleadingly half-working image. Drop the hipblas variant rather than shipping a partially accelerated build users can't distinguish from the real thing. AMD hosts now fall through the capability map to cpu-whisperx / cpu-whisperx-development. Also removes the now-dangling rocm-whisperx assertion from pkg/system/capabilities_test.go and the ROCm mention from the whisperx row in docs/content/reference/compatibility-table.md. Assisted-by: Claude Code:claude-opus-4-7 |
||
|---|---|---|
| .. | ||
| disabled | ||
| backend.yml | ||
| backend_build.yml | ||
| backend_build_darwin.yml | ||
| backend_pr.yml | ||
| build-test.yaml | ||
| bump-inference-defaults.yml | ||
| bump_deps.yaml | ||
| bump_docs.yaml | ||
| checksum_checker.yaml | ||
| deploy-explorer.yaml | ||
| gallery-agent.yaml | ||
| generate_grpc_cache.yaml | ||
| generate_intel_image.yaml | ||
| gh-pages.yml | ||
| image-pr.yml | ||
| image.yml | ||
| image_build.yml | ||
| notify-releases.yaml | ||
| release.yaml | ||
| secscan.yaml | ||
| stalebot.yml | ||
| test-extra.yml | ||
| test.yml | ||
| tests-e2e.yml | ||
| tests-ui-e2e.yml | ||
| update_swagger.yaml | ||
| yaml-check.yml | ||