Joshna-Medisetty 191b9a8dbf Voxtral TTS: drop hardcoded CUDA in audio tokenizer; add XPU stage config (#2428) ...

Signed-off-by: Joshna Medisetty <joshna.medisetty@intel.com>
Signed-off-by: Joshna-Medisetty <joshna.medisetty@intel.com>

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

..

configuration_voxtral_tts.py

[Model] Add Voxtral TTS model (#1803)

2026-03-19 16:02:11 -04:00

cuda_graph_acoustic_transformer_wrapper.py

[Voxtral TTS] Use 8 step flow matching instead of 16 (#2158)

2026-03-25 04:33:18 +00:00

voxtral_tts_audio_generation.py

[Rebase] Rebase to vllm v0.19.0 (#2475)

2026-04-04 15:03:32 +08:00

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

[Bugfix] Fix Voxtral TTS voice embeddings not loading (#2156)

2026-03-26 21:34:31 +08:00