Files
LocalAI/.github
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
..
2023-07-09 13:39:00 +02:00
2025-02-13 09:58:19 +01:00