holykie aa2fadac42 [Perf][Diffusion] Activate NPU/GPU matmul for LoRA delta computation when weights are on CPU (#7590) ...

Signed-off-by: holykie <116775684+holykie@users.noreply.github.com>

2026-09-18 16:51:23 +08:00

..

layers

[Perf][Diffusion] Keep LoRA weights resident across activation cycles (#7195)

2026-09-07 14:27:24 +00:00

__init__.py

[Feature] Diffusion LoRA Adapter Support (PEFT compatible) for vLLM alignment (#758)

2026-01-27 10:22:40 +08:00

loader.py

[Perf][Diffusion] Activate NPU/GPU matmul for LoRA delta computation when weights are on CPU (#7590)

2026-09-18 16:51:23 +08:00

manager.py

[Refactor][Diffusion] Remove model-specific names from LoRA and ModelOpt loader defaults (#5907)

2026-09-12 20:30:03 +08:00

utils.py

[ROCm] [CI] Fix circular import for rocm due to patch (#6287)

2026-08-18 09:45:05 +00:00