Yueqian Lin d7b365df64 [Bugfix][Qwen3-TTS] Keep seeded residual MTP sampling batched (#4889) ...

Signed-off-by: Yueqian Lin <linyueqian@outlook.com>

2026-07-05 21:47:06 +08:00

..

__init__.py

feat(qwen3-tts): Add CUDA Graph support for speech tokenizer decoder (#1205)

2026-02-27 10:48:25 +08:00

test_code_predictor_dtype.py

[Bugfix][Qwen3-TTS] Keep seeded residual MTP sampling batched (#4889)

2026-07-05 21:47:06 +08:00

test_cuda_graph_decoder.py

[Bugfix][Qwen3-Omni] Fix Code2Wav CUDA-graph output length surplus (#4466) (#4525)

2026-06-19 23:58:45 -07:00

test_qwen3_tts_code2wav.py

Qwen3-TTS full-payload: emit empty-finished payload on degenerate take instead of dropping (fixes Stage-1 300s hang) (#4465)

2026-06-23 00:21:11 +00:00

test_qwen3_tts_talker_preprocess.py

[Bugfix] Qwen3-TTS talker handles multi-token replay on resume (#4559)

2026-07-02 04:46:05 +00:00

test_qwen3_tts_talker_prompt_len.py

[Feature] Add precomputed custom voices and Qwen3-TTS ref-context cache (#3492)

2026-05-31 17:51:24 +00:00

test_qwen3_tts_talker_ref_codes.py

[Bugfix] Qwen3-TTS talker handles multi-token replay on resume (#4559)

2026-07-02 04:46:05 +00:00