3 people e1088026fa [Performance] Improve MiMo-Audio tokenizer decoding performance (#2183) ...

Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
Co-authored-by: Jialong Liu <88185941+Galleons2029@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

2026-05-11 10:05:46 +08:00

..

layers

[Cleanup] Extract shared SinusPositionEmbedding/DiTTimestepEmbedding/timestep_embedding layer (#3285)

2026-05-01 20:19:42 +08:00

model_loader

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

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

models

[Performance] Improve MiMo-Audio tokenizer decoding performance (#2183)

2026-05-11 10:05:46 +08:00

stage_configs

[Perf] Fix Qwen3-TTS latency regression (#3485)

2026-05-10 23:07:38 +00:00

stage_input_processors

[Perf] Fix Qwen3-TTS latency regression (#3485)

2026-05-10 23:07:38 +00:00

__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