LocalAI

mirror of https://github.com/mudler/LocalAI.git synced 2026-04-30 03:55:58 -04:00

Files

Ettore Di Giacinto 39573ecd2a chore(whisperx): drop ROCm/hipblas build target (#9474 )

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

2026-04-21 21:50:18 +02:00

backend.py

feat: add distributed mode (#9124 )

2026-03-30 00:47:27 +02:00

install.sh

fix: try to add whisperx and faster-whisper for more variants (#9278 )

2026-04-08 21:23:38 +02:00

Makefile

feat(whisperx): add whisperx backend for transcription with speaker diarization (#8299 )

2026-02-02 16:33:12 +01:00

protogen.sh

feat(whisperx): add whisperx backend for transcription with speaker diarization (#8299 )