Juan Pablo ZuluagaandYueqian Lin 5358f5db01 [Perf][TTS] omnivoice hot path: D2H batching, mask caching, cached text embeddings (#5174) ...

Signed-off-by: JuanPZuluaga <juanz9312@gmail.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>

2026-08-12 17:15:35 +00:00

..

__init__.py

[OmniVoice] Add two-stage TTS serving support (#2463)

2026-04-03 20:41:20 +00:00

duration.py

[OmniVoice] Add two-stage TTS serving support (#2463)

2026-04-03 20:41:20 +00:00

omnivoice_decoder.py

[Perf] [OmniVoice] Triton kernel fusion + CUDA Graph acceleration (#3336)

2026-05-22 13:12:47 +00:00

omnivoice_generator.py

[Perf][TTS] omnivoice hot path: D2H batching, mask caching, cached text embeddings (#5174)

2026-08-12 17:15:35 +00:00

omnivoice.py

[Refactor] Replace hardcoded CUDA device selection with platform-agnostic API (#4496)

2026-06-23 14:38:32 +08:00

pipeline.py

[Config] Return VllmOmniConfig from create_from_model (#4818)

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