3 people f6e3dece09 [Feature] Add FP8 quantization for Voxtral TTS (#3036) ...

Signed-off-by: akshatvishu <akshatnayak197@gmail.com>
Signed-off-by: Chen-Yo Sun <chenyo.sun@mistral.ai>
Signed-off-by: akshatvishu <33392262+akshatvishu@users.noreply.github.com>
Co-authored-by: Chen-Yo Sun <chenyo.sun@mistral.ai>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>

2026-05-08 22:40:36 -04:00

..

__init__.py

[Config Refactor] Migrate 5 TTS models (VoxCPM2 / CosyVoice3 / MiMo Audio / Voxtral TTS / Fish Speech S2 Pro) to Pipeline + Deploy schema (#2958)

2026-04-21 21:17:53 +08:00

cuda_graph_acoustic_transformer_wrapper.py

[Refactor] Replace and ban a few torch.cuda functions in favor of torch.accelerator replacements. (#3365)

2026-05-07 23:23:59 +08:00

pipeline.py

[Config Refactor] Migrate 5 TTS models (VoxCPM2 / CosyVoice3 / MiMo Audio / Voxtral TTS / Fish Speech S2 Pro) to Pipeline + Deploy schema (#2958)

2026-04-21 21:17:53 +08:00

voxtral_tts_audio_generation.py

[Feature] Add FP8 quantization for Voxtral TTS (#3036)

2026-05-08 22:40:36 -04:00

voxtral_tts_audio_tokenizer.py

Voxtral TTS: drop hardcoded CUDA in audio tokenizer; add XPU stage config (#2428)

2026-04-04 07:04:04 +00:00

voxtral_tts.py

[Feature] Add FP8 quantization for Voxtral TTS (#3036)

2026-05-08 22:40:36 -04:00