ARAVINDHAN Tandlinitra24 e58f8dde7f [Bugfix] Use FusedMoEWithLoRA for shared MoE LoRAs on 3D models (#60098) ...

Signed-off-by: ARAVINDHAN T <arvindhant01@gmail.com>
Co-authored-by: linitra24 <renshuang.zhou@daocloud.io>

2026-10-08 15:04:32 +08:00

..

layers

[LoRA] Support variable num_labels for sequence classification (#57766)

2026-09-28 14:58:35 +00:00

ops

[Kernel][LoRA] Add deterministic split-K=8 LoRA shrink for batch invariance (#59377)

2026-10-04 18:46:16 -04:00

punica_wrapper

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

__init__.py

[Experimental] Add multi-LoRA support (#1804)

2024-01-23 15:26:37 -08:00

lora_model.py

[LoRA] Remove tensorizer (#60024)

2026-10-05 07:01:56 -07:00

lora_weights.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

model_manager.py

[Bugfix] Use FusedMoEWithLoRA for shared MoE LoRAs on 3D models (#60098)

2026-10-08 15:04:32 +08:00

peft_helper.py

[LoRA] Remove tensorizer (#60024)

2026-10-05 07:01:56 -07:00

request.py

[LoRA] Remove tensorizer (#60024)

2026-10-05 07:01:56 -07:00

resolver.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

utils.py

[Bugfix] Load stacked expert weights for non-gated MoE (#59031)

2026-10-05 15:26:55 +03:00

worker_manager.py

[LoRA] Remove tensorizer (#60024)

2026-10-05 07:01:56 -07:00