andyluo7 09d704907f fix: preserve Torch seeded sampling on ROCm (#8341) ...

Signed-off-by: andyluo7 <andy.luo@amd.com>

2026-10-04 16:03:21 +13:00

..

__init__.py

[Hardware] Support platforms and plugin system (#774)

2026-01-28 22:12:52 +08:00

audio_resample.py

[Core][Frontend] Unified Full-duplex Framework (#7413)

2026-09-16 15:35:36 +08:00

audio.py

[Refactor][OutputProcessor 2/8]: OmniRequestOutput should inherit RequestOutput and no nested wrap-up (#5146)

2026-08-12 22:58:23 +08:00

custom_voice_io.py

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

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

device_copy.py

[Core] Extend the shared multi-stage execution framework for mixed V1/MRv2 pipelines (#8184)

2026-09-29 07:40:57 -07:00

forced_aligner.py

[Bugfix] Fix Qwen3-TTS word timestamps with async chunking (#7544)

2026-09-16 15:07:52 -07:00

mm_outputs.py

[New Model] Support IndexTTS 2.5 (#5957)

2026-08-11 23:00:35 +00:00

qwen3_force_align_processor.py

[Bugfix] Build the forced-aligner prompt without a chat template (word timestamps one bin late) (#7240)

2026-09-08 19:27:38 +00:00

seeded_exponential.py

fix: preserve Torch seeded sampling on ROCm (#8341)

2026-10-04 16:03:21 +13:00

speaker_cache.py

[Frontend] Tune reference cache limits and registered MOSS voice requests (#7883)

2026-09-29 04:10:17 +00:00

tracking_parser.py

[Frontend] Scale Omni serving across API processes (#6923)

2026-09-16 22:29:31 -07:00