andyluo7andwangyu 36b74f99f6 test: keep Hunyuan LoRA CPU path on native linear (#8166) ...

Signed-off-by: andyluo7 <andy.luo@amd.com>
Co-authored-by: wangyu <53896905+yenuo26@users.noreply.github.com>

2026-09-28 04:33:40 +00:00

..

helpers.py

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

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

test_base_linear.py

[Core] Optimize diffusion LoRA expand accumulation (#6268)

2026-09-03 10:37:35 +08:00

test_diffusion_lora.py

[Refactor][OutputProcessor 2/8]: OmniRequestOutput should inherit RequestOutput and no nested wrap-up (#5146)

2026-08-12 22:58:23 +08:00

test_images_generations_lora.py

[ROCm] [CI] Migrate CI to mi300x for v0.27.x (#5886)

2026-08-14 15:38:47 +08:00

test_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

test_lora_manager.py

test: keep Hunyuan LoRA CPU path on native linear (#8166)

2026-09-28 04:33:40 +00:00