yangyonggit 63ba11b8b1 [Perf] Stacked audio ops: batched matmul and embedding gather in MOSS-TTS talker (#4230) ...

Signed-off-by: leo.yang <leo.yang.engineer@gmail.com>

2026-06-19 00:38:32 +00:00

..

__init__.py

[TTS][Model] support MOSS-TTS series (#3420)

2026-06-02 15:46:01 +08:00

audio_tokenizer.py

[TTS][Model] support MOSS-TTS series (#3420)

2026-06-02 15:46:01 +08:00

configuration_moss_tts.py

[TTS][Model] support MOSS-TTS series (#3420)

2026-06-02 15:46:01 +08:00

modeling_moss_tts_codec.py

feat(moss-tts): add CUDA Graph support for codec decoder (#4157)

2026-06-11 22:17:31 +00:00

modeling_moss_tts_local.py

[TTS][Model] support MOSS-TTS series (#3420)

2026-06-02 15:46:01 +08:00

modeling_moss_tts_talker.py

[Perf] Stacked audio ops: batched matmul and embedding gather in MOSS-TTS talker (#4230)

2026-06-19 00:38:32 +00:00

moss_codec_cudagraph.py

feat(moss-tts): add CUDA Graph support for codec decoder (#4157)

2026-06-11 22:17:31 +00:00

pipeline.py

[TTS][Model] support MOSS-TTS series (#3420)

2026-06-02 15:46:01 +08:00

reference_encoder.py

[TTS][Model] support MOSS-TTS series (#3420)

2026-06-02 15:46:01 +08:00