Xin Yang ecc3dd66cc [Bugfix] Fix FusedMoE LoRA kernel offs_token out of bound value (#32279) ...

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

2026-01-24 01:41:35 +00:00

..

layers

[Quantization][Deprecation] Deprecate HQQ (#32681)

2026-01-21 09:32:40 -05:00

ops

[Bugfix] Fix FusedMoE LoRA kernel offs_token out of bound value (#32279)

2026-01-24 01:41:35 +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

Add support for LoRA adapters in Nemotron-H models (#30802)

2026-01-19 22:30:44 +08:00

model_manager.py

Add support for LoRA adapters in Nemotron-H models (#30802)

2026-01-19 22:30:44 +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

[Feat] allow inplace loading lora (#31326)

2026-01-20 10:15:20 +08:00

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] ModelScope is supported when downloading LORA models. (#32844)

2026-01-22 16:33:21 +00:00

worker_manager.py

[Feat] allow inplace loading lora (#31326)

2026-01-20 10:15:20 +08:00