fatSheepandamy-why-3459 5d44868e91 [Hardware][Ascend] Keep HiFT vocoder on NPU (#5242) ...

Signed-off-by: fatSheep <tzh2005t@163.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>

2026-07-21 14:30:30 +08:00

..

_310p

[Hardware][Ascend][Model] Optimize Qwen3-TTS on 310P (#4841)

2026-07-15 08:57:44 +08:00

models

[Hardware][Ascend] Keep HiFT vocoder on NPU (#5242)

2026-07-21 14:30:30 +08:00

omni_connectors

Yuanrong TransferEngine Connector for NPU (#3180)

2026-05-20 14:51:33 +08:00

quant

support online FP8 quantization for FA on NPU #2236 (#2640)

2026-05-13 11:46:00 +08:00

worker

[Bugfix] Drop out-of-vocabulary stop ids from min-tokens masking (qwen3-tts min_tokens engine crash) (#4971)

2026-07-08 11:24:31 -07:00

__init__.py

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

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

platform.py

[Refactor] Migrate Legacy Stage Configs to the Pipeline Registry (#5031)

2026-07-18 09:34:33 +00:00

profiler.py

[Refactor] Unify torch profiler for omni and diffusion models (#2099)

2026-03-24 15:25:52 +08:00