xpu enabling for 4 cases #12345
Merged
xpu enabling for 4 cases #12345
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: Yao, Matrix <[email protected]>
yao-matrix
commented
Sep 18, 2025
|
|
||
| def enable_auto_cpu_offload(self, device: Union[str, int, torch.device] = "cuda", memory_reserve_margin="3GB"): | ||
| def enable_auto_cpu_offload(self, device: Union[str, int, torch.device] = None, memory_reserve_margin="3GB"): | ||
| """ |
There was a problem hiding this comment.
as in #11288, i suggest make None as the default value of device, so in that case, if users run on other devices like XPU w/o specify the device argument, the code will auto detect the device and run, rather than crash. Thx
|
@DN6 @a-r-r-o-w , could you pls take a review? Thx very much. |
DN6
approved these changes
Sep 24, 2025
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
to make below 4 cases pass on XPU
pytest -rA tests/modular_pipelines/stable_diffusion_xl/test_modular_pipeline_stable_diffusion_xl.py::SDXLImg2ImgModularPipelineFastTests::test_components_auto_cpu_offload_inference_consistent
pytest -rA tests/modular_pipelines/stable_diffusion_xl/test_modular_pipeline_stable_diffusion_xl.py::SDXLInpaintingModularPipelineFastTests::test_components_auto_cpu_offload_inference_consistent
pytest -rA tests/modular_pipelines/stable_diffusion_xl/test_modular_pipeline_stable_diffusion_xl.py::SDXLModularPipelineFastTests::test_components_auto_cpu_offload_inference_consistent
pytest -rA tests/lora/test_lora_layers_hunyuanvideo.py::HunyuanVideoLoRAIntegrationTests::test_original_format_cseti
@DN6 @a-r-r-o-w , pls help review, thx very much