3 people 5351cd6645 [Bugfix] Qwen3-Omni thinker: create deepstack buffers on the real device (#8461) ...

Signed-off-by: John Nunez <johnnynunez@users.noreply.github.com>
Co-authored-by: John Nunez <johnnynunez@users.noreply.github.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>

2026-10-05 21:00:04 +08:00

..

common

[Core][Model] Fit PersonaPlex into the Unified Full-duplex Framework (RFC #7181 PR 2) (#7695)

2026-09-27 03:02:24 +00:00

layers

Add NPU support for OmniMRotaryEmbedding (#3609)

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

model_loader

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

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

models

[Bugfix] Qwen3-Omni thinker: create deepstack buffers on the real device (#8461)

2026-10-05 21:00:04 +08:00

stage_input_processors

[Model][Core] Avoid unused CosyVoice3 payloads and redundant AR output work (#8473)

2026-10-05 04:52:19 +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

duplex_sampling.py

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

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

output_snapshot.py

[Model] Optimize MOSS Local 1.5 MRV2 serving and progressive chunks (#8213)

2026-10-02 18:03:14 +00:00