Tianyao WuandClaude 1b7e854b05 [Bugfix][MiniCPM-o] Attach a unit's whole frame group and size the vision slot budget like Stage0 (#7271) ...

Signed-off-by: Tianyao Wu <rayroy31@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>

2026-09-14 15:25:34 -07:00

..

duplex

[Bugfix][MiniCPM-o] Attach a unit's whole frame group and size the vision slot budget like Stage0 (#7271)

2026-09-14 15:25:34 -07:00

__init__.py

[Bugfix][MiniCPM-o] Bound full-duplex Talker context with sliding recompute (#6626)

2026-08-30 00:49:42 +08:00

batched_token2wav.py

[Feature][MiniCPM-o] Support configurable concurrent duplex sessions (#6021)

2026-08-25 02:27:30 +00:00

cuda_graph_wrapper.py

[Bugfix][MiniCPM-o] Retire CFM DiT CUDA graphs a generation at a time (#6587)

2026-08-28 14:07:57 +08:00

minicpmo_4_5_code2wav.py

Add vLLM-Omni library info to Hugging Face Hub requests (#5381)

2026-09-08 10:08:38 -06:00

minicpmo_4_5_omni_llm.py

[Bugfix][MiniCPMO45] Return bare tensor in Thinker forward to fix repetition loop (#7497) (#7517)

2026-09-14 21:11:15 +08:00

minicpmo_4_5_omni_tts.py

[Model] Preserve MiniCPM-o Talker full attention until capacity (#6799)

2026-09-06 22:25:35 +08:00

minicpmo_4_5_omni.py

[Bugfix][MiniCPMO45] Return bare tensor in Thinker forward to fix repetition loop (#7497) (#7517)

2026-09-14 21:11:15 +08:00

minicpmo_4_5_token2wav.py

[Perf][MiniCPM-o] TensorRT acceleration for the Code2Wav vocoder (DiT estimator + campplus) (#5638)

2026-08-04 20:58:19 -07:00

pipeline.py

[Model] Stop MiniCPM-o Thinker at TTS boundaries (#7463)

2026-09-14 15:25:00 -07:00