Sy03andYueqian Lin f6cfacdd16 [Perf][Qwen3-TTS] Free unused decoder in Talker SpeechTokenizer to VRAM (#2429) ...

Signed-off-by: Sy03 <1370724210@qq.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>

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

..

layers

Update MRoPE config fallback logic (#2278)

2026-04-02 16:28:53 +00:00

model_loader

[Fix]Ensure HuggingFace downloads complete before initialization. (#1213)

2026-02-10 16:05:12 +08:00

models

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

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

stage_configs

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

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

stage_input_processors

[Model][Core] Enable async_chunk streaming pipeline for CosyVoice3 (#1703)

2026-04-05 06:11:33 +00:00

__init__.py

update ar_dit_test

2025-09-28 21:58:48 +08:00

custom_process_mixin.py

[Core] customize process between stages, remove the need of "request_ids" in model forward, rebase to 0.12.0 (#458)

2025-12-24 13:26:33 +00:00