amy-why-3459 5dc787d5e8 [Perf][Qwen3-TTS] Align talker MTP CUDA graph capture with Qwen3-Omni & Adapt to async output (#4923) ...

Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>

2026-07-10 11:11:29 +08:00

..

layers

Add NPU support for OmniMRotaryEmbedding (#3609)

2026-06-18 16:58:40 +08:00

model_loader

[Fix]Ensure HuggingFace downloads complete before initialization. (#1213)

2026-02-10 16:05:12 +08:00

models

[Perf][Qwen3-TTS] Align talker MTP CUDA graph capture with Qwen3-Omni & Adapt to async output (#4923)

2026-07-10 11:11:29 +08:00

stage_configs

[Refactor] Migrate MammothModa2 and OmniVoice to pipeline registry (#4647)

2026-07-08 00:44:33 +00:00

stage_input_processors

[Feature] Support MOSS-TTS-Local-v1.5 Streaming (#4804)

2026-07-03 16:00:30 +08:00

__init__.py

update ar_dit_test

2025-09-28 21:58:48 +08:00

custom_process_mixin.py

[Core] customize process between stages, remove the need of "request_ids" in model forward, rebase to 0.12.0 (#458)

2025-12-24 13:26:33 +00:00