tzhouam 008fa25263 Merge main into dev/vllm-align for vLLM 0.31 release ...

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

2026-10-03 21:05:17 +08:00

..

code2wav_core

[Model] Optimize CosyVoice3 packed streaming with bounded HiFT graphs (#8420)

2026-10-02 08:49:50 -07:00

__init__.py

[Model] Fun cosy voice3-0.5-b-2512 (#498)

2026-03-04 19:54:59 -05:00

cosyvoice3_code2wav.py

[Model] Optimize CosyVoice3 packed streaming with bounded HiFT graphs (#8420)

2026-10-02 08:49:50 -07:00

cosyvoice3_talker.py

[Model] Fun cosy voice3-0.5-b-2512 (#498)

2026-03-04 19:54:59 -05:00

cosyvoice3.py

fix: preserve Omni processor conditioning on vLLM 0.31

2026-10-03 21:03:26 +08:00

flow_estimator_trt.py

[Bugfix][TTS] Make CosyVoice3 TRT plan publication concurrency-safe (#6955)

2026-09-03 06:44:42 +00:00

pipeline.py

[Refactor][2/N Scheduler]Replace _FULL_PAYLOAD_INPUT_STAGES with a resolved stage transport capability. (#6149)

2026-08-25 15:24:59 +08:00

ras_sampler.py

[Model] Add opt-in packed Flow and batched HiFT inference for CosyVoice3 (#8224)

2026-09-29 15:48:36 +00:00

runtime.py

[Model] Add opt-in packed Flow and batched HiFT inference for CosyVoice3 (#8224)

2026-09-29 15:48:36 +00:00

speaker_embedding_trt.py

[Perf][TTS] Optimize cosyvoice TTFP and throughput using TensorRT (#4168)

2026-06-10 16:42:34 +08:00

tokenizer.py

[Model] Fun cosy voice3-0.5-b-2512 (#498)

2026-03-04 19:54:59 -05:00

utils.py

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

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