make `pipelines` tests device-agnostic (part1)
What does this PR do?
Below are some evidences:
PASSED tests/pipelines/animatediff/test_animatediff.py::AnimateDiffPipelineFastTests::test_to_device
PASSED tests/pipelines/amused/test_amused.py::AmusedPipelineFastTests::test_model_cpu_offload_forward_pass
PASSED tests/pipelines/amused/test_amused.py::AmusedPipelineFastTests::test_cpu_offload_
forward_pass_twice
PASSED tests/pipelines/amused/test_amused_inpaint.py::AmusedInpaintPipelineFastTests::te
st_to_device
@yiyixuxu
Could you provide some details about the machine you used to run the tests changed in this PR?
Could you provide some details about the machine you used to run the tests changed in this PR?
yes, I am running on Intel(R) Data Center GPU Max 1550.
Could you provide some details about the machine you used to run the tests changed in this PR?
xpu is the common device name for intel gpu.
Hi @sayakpaul , any concern on this PR?
could you pls help retrigger the CI? Thx a lot!
I saw the failed CI tests. Is this because that those tests should only run on CUDA devices? @yiyixuxu
I saw the failed CI tests. Is this because that those tests should only run on CUDA devices? @yiyixuxu
Correct
Okay, updated!
There are 1705 cuda-only UTs. Besides this PR, I have more PRs coming related to device-agnostic tests, e.g. (9401, 9400). Could you pls take a look at this one, so I can proceed with the rest? Thanks a lot!
Hi @yiyixuxu, could you let me know your thoughts on this PR?
Hi folks, 2 weeks already, any feedback? I am waiting to enable more cases on XPU... If this is not the right approach, pls let me know as well. Thanks a lot!
@sayakpaul @yiyixuxu
Please be a little more respectful towards the maintainers' time. It will be reviewed soon.
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.
Please be a little more respectful towards the maintainers' time. It will be reviewed soon.
oh, if my expression sounds impolite, sorry for that. And thanks for letting me know!
No hurries, I am just a bit worried that I might not be on the right track. Thanks for your understanding.
Please be a little more respectful towards the maintainers' time. It will be reviewed soon.
@sayakpaul , could you pls take a review on this? This PR and following PRs are part of efforts to integrate intel gpu into hugging face ecosystems and making CIs can run as expected, thx.
@yiyixuxu thanks for the comments. I went through all the changes again and updated the places when necessary. Pls have a review. Thx!
Hi @yiyixuxu , can we move forward with this PR?
Hi guys, any concern about this PR?
Thanks for the comments. Code Update!
@faaany can you please run styling on this branch and apply the same comments to part 2 PR ? (require_non_cpu is still defined and used there)
@faaany can you please run styling on this branch and apply the same comments to part 2 PR ? (
require_non_cpuis still defined and used there)
Thanks for the review! Style fixed and let me un-draft the part2 PR, once this one got merged
@faaany your changes didn't pass the code quality check, can you do make style && make quality
@faaany your changes didn't pass the code quality check, can you do
make style && make quality
done
Hi @DN6 , could you take a look at this PR?