-
Notifications
You must be signed in to change notification settings - Fork 31.3k
Compress #42643
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Compress #42643
Conversation
|
[For maintainers] Suggested jobs to run (before merge) run-slow: compressed_tensors_integration |
|
run-slow: compressed_tensors_integration |
|
cc @yao-matrix |
|
Hi @ydshieh . Could you please review this PR? Thanks! |
| torch.equal( | ||
| submodule.weight.to(torch_device), comp_decomp_obj.weight.to(torch_device) | ||
| ), |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
You have seen that these 2 could be on different device?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yes, I run it on A100 and got the device error:
FAILED tests/quantization/compressed_tensors_integration/test_compressed_models.py::StackCompressedModelTest::test_compressed_uncompressed_model_shapes - RuntimeError: Expected all tensors to be on the same device, but got other is on cuda:1, different from other tensors on cuda:0 (wh...
MekkCyber
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Sounds good! Thanks for fixing
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
SunMarc
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks !
|
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. |
* fix compressed tensor tests Signed-off-by: jiqing-feng <[email protected]> * update Signed-off-by: jiqing-feng <[email protected]> * update comment Signed-off-by: jiqing-feng <[email protected]> * format Signed-off-by: jiqing-feng <[email protected]> --------- Signed-off-by: jiqing-feng <[email protected]>
Fix xpu tests in compressed tensors by mapping different expect outputs.