Nick CaoandClaude 149b9f179a [Perf][Qwen3-TTS][Voxtral-TTS] Share CUDA graph memory pool across decoder capture sizes (#2386) ...

Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>

2026-04-08 20:40:17 -04:00

..

tokenizer_12hz

[Feat][Qwen3TTS][Code2wav] triton SnakeBeta and Cuda Graph (#1797)

2026-03-20 12:11:37 +08:00

tokenizer_25hz

[Cleanup] Replace bare print() with logger and use specific exception types (#2228)

2026-04-03 23:59:07 +08:00

__init__.py

[Model] Support Qwen3-TTS model series (#895)

2026-01-22 16:57:37 +08:00

configuration_qwen3_tts.py

[Bugfix] Fix Qwen3TTSConfig init order to be compatible with newer Tansformers(5.x) (#2306)

2026-03-30 09:50:16 +08:00

cuda_graph_decoder_wrapper.py

[Perf][Qwen3-TTS][Voxtral-TTS] Share CUDA graph memory pool across decoder capture sizes (#2386)

2026-04-08 20:40:17 -04:00

pipeline.yaml

[Fix] [Qwen3-TTS] Qwen3-TTS streaming chunk-boundary artifacts (#2480)

2026-04-05 14:40:38 -04:00

qwen3_tts_code2wav.py

[Fix] [Qwen3-TTS] Qwen3-TTS streaming chunk-boundary artifacts (#2480)

2026-04-05 14:40:38 -04:00

qwen3_tts_code_predictor_vllm.py

fix(qwen3_tts): align code predictor buffer dtype with model parameters (#2470)

2026-04-05 20:54:15 +00:00

qwen3_tts_talker.py

[Perf][Qwen3-TTS] Free unused decoder in Talker SpeechTokenizer to VRAM (#2429)

2026-04-05 19:04:37 +00:00

qwen3_tts_tokenizer.py

[Bugfix][Qwen3TTS] (#1289)

2026-02-26 18:58:35 +08:00