3 Commits

Include renames

Author	SHA1	Message	Date
Ettore Di Giacinto	f8e228e0ba	fix(fish-speech): support CUDA 13 on arm64 ... Keep the relocated upstream source importable, select CUDA 13 PyTorch wheels instead of the aarch64 CPU fallback, and decode reference audio without torchcodec, which has no Linux arm64 wheels. Assisted-by: Codex:gpt-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2026-09-11 21:48:07 +00:00
localai-org-maint-botandlocalai-org-maint-bot	411fdf10c3	fix(fish-speech): preserve ROCm PyTorch (#11568) ... The upstream editable install pins generic PyTorch packages. It replaces the HIP wheels with CUDA wheels in ROCm images. Remove those pins only for hipBLAS builds before the editable install. Keep the existing CPU and CUDA dependency behavior unchanged. Assisted-by: Codex:gpt-5 Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>	2026-08-18 08:58:38 +02:00
Ettore Di Giacinto	7dc691c171	feat: add fish-speech backend (#8962) ... * feat: add fish-speech backend Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * drop portaudio Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2026-03-12 07:48:23 +01:00