bnellnm 7cf56a59a2 [MoE Refactor] Make SharedExperts class for use with DefaultMoERunner (#35153) ...

Signed-off-by: Bill Nell <bnell@redhat.com>

2026-04-01 09:44:08 -04:00

..

layers

[MoE Refactor] Make SharedExperts class for use with DefaultMoERunner (#35153)

2026-04-01 09:44:08 -04:00

ops

[Bugfix][ROCm][MoE] Fix mxfp4 oracle regressions from #37128 (#37787)

2026-03-25 08:17:33 +08:00

punica_wrapper

use 'max_active_experts' for moe lora input size (#33197)

2026-02-27 03:50:43 +00:00

__init__.py

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

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

lora_model.py

[Bugfix][CI] fix typos (#34934)

2026-03-05 17:05:46 +00:00

lora_weights.py

[Misc] Replace Optional[X] with X | None syntax (#33332)

2026-01-30 01:56:59 -08:00

model_manager.py

[LoRA] Minor improvements to LoRA log (#37557)

2026-03-19 15:18:06 +00:00

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

[Kernel] Add gpt-oss Router GEMM kernel (#37205)

2026-03-18 08:15:56 -07:00

worker_manager.py

[Bugfix][LoRA] Fix incorrect LoRA Log (#37877)

2026-03-23 11:42:52 +00:00