Ethan Yang

> @openvino-dev-samples looks like you need to add qwen3 and qwen3-moe to `EXPECTED_NUM_SDPA` > > https://github.com/huggingface/optimum-intel/blob/f53b878b98f7680902e83f869767dc62d69038ac/tests/openvino/test_modeling.py#L1153 > > to give the expected number of SDPA to fix the following tests...

> Questions, as an Intel Arc owner and having contributed to the repository. > > 1.) I have used both the Triton(`inductor`) and OpenVINO backends using custom nodes and Triton...

> python3 main.py --cpu --use-pytorch-cross-attention I think it can supp > Sorry for double post, but wondering, does loading a lora, then disabling it, and then enabling it again works...

> > python3 main.py --cpu --use-pytorch-cross-attention > > I think it can supp > > > Sorry for double post, but wondering, does loading a lora, then disabling it, and...

hi @comfyanonymous could you help to review ?

Hi @NineMeowICT Could you help to check if this PR is ready to be merged ? thanks

> @openvino-dev-samples Appreciate you working on implementing this, currently using your fork, it dosent seem to be using the gpu for the inference even tho ive selected gpu as the...

> > > @openvino-dev-samples Appreciate you working on implementing this, currently using your fork, it dosent seem to be using the gpu for the inference even tho ive selected gpu...

> > Thank you for looking, but i resolved the problem. It was the low memory which was causing it to go back to cpu, Increasing memory helped resolve this....

> Hey, sorry that this did not get an official review for so long! > > For the lora fix for torch.compile, even with the keys workaround, there was indeed...