Xin Yang a884bc62d6 [LoRA] Update LoRA expand kernel heuristic (#32425) ...

Signed-off-by: Xin Yang <xyangx@amazon.com>

2026-01-16 18:38:07 +00:00

..

layers

[LoRA][Perf] Improve FusedMoE LoRA performance for small rank (#32019)

2026-01-10 11:04:18 -08:00

ops

[LoRA] Update LoRA expand kernel heuristic (#32425)

2026-01-16 18:38:07 +00:00

punica_wrapper

[Refactor][TPU] Remove torch_xla path and use tpu-inference (#30808)

2026-01-07 16:07:16 +08:00

__init__.py

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

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

lora_model.py

[Bugfix] Fix MoE LoRA bin/pt loading (#31161)

2025-12-23 19:09:15 +08:00

lora_weights.py

[LoRA] Continue optimizing MoE LoRA weight loading (#29322)

2025-11-27 05:56:28 -08:00

model_manager.py

[2/N] Move cache factories to MM registry (#32382)

2026-01-15 01:02:30 -08:00

peft_helper.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

request.py

[Misc] Fix Qwen2-MoE shared_expert_gate (#31339)

2025-12-26 05:10:39 +00:00

resolver.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

utils.py

[Bugfix] Fix MoE LoRA bin/pt loading (#31161)

2025-12-23 19:09:15 +08:00

worker_manager.py

[Core] Initialize LoRA support for tower and connector in multi-modal models (#26674)

2025-12-26 04:48:20 -08:00