3 people af2f84582b perf(qwen3-tts): cache decoder masks and compile pre-transformer (#5107) ...

Signed-off-by: Ziyang Zhang <hafuhafu@qq.com>
Co-authored-by: Sy03 <1370724210@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

2026-07-25 08:09:19 +00:00

..

tokenizer_12hz

perf(qwen3-tts): cache decoder masks and compile pre-transformer (#5107)

2026-07-25 08:09:19 +00:00

tokenizer_25hz

[Chore][TTS] Reference recipes.vllm.ai recipes, remove dead code, and fix stale references (#4567)

2026-06-19 15:05:26 +08:00

__init__.py

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

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

configuration_qwen3_tts.py

[Chore][TTS] Reference recipes.vllm.ai recipes, remove dead code, and fix stale references (#4567)

2026-06-19 15:05:26 +08:00

cuda_graph_decoder_wrapper.py

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

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

pipeline.py

[Config] Return VllmOmniConfig from create_from_model (#4818)

2026-07-18 09:21:07 +00:00

prompt_embeds_builder.py

[Chore][TTS] Reference recipes.vllm.ai recipes, remove dead code, and fix stale references (#4567)

2026-06-19 15:05:26 +08:00

qwen3_tts_code2wav.py

[Perf][Bugfix] qwen3-tts hot path: prefix-cache OOM guards + talker/orchestrator micro-opts (#3689)

2026-06-09 10:36:57 -07:00

qwen3_tts_code_predictor_vllm.py

[Perf][Qwen3-TTS] Align talker MTP CUDA graph capture with Qwen3-Omni & Adapt to async output (#4923)

2026-07-10 11:11:29 +08:00

qwen3_tts_talker.py

[Perf][Qwen3-TTS] Align talker MTP CUDA graph capture with Qwen3-Omni & Adapt to async output (#4923)

2026-07-10 11:11:29 +08:00

qwen3_tts_tokenizer.py

[Refactor] Remove resampy dependency (#2891)

2026-04-18 03:20:36 +00:00