Open
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/4191
Note: Links to docs will display an error until the docs builds have been completed. ❌ 8 New FailuresAs of commit 950b4fb with merge base 4611835 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
xiaowangintel
added
module: inference
liangan1
reviewed
Mar 30, 2026
| if device == "cuda": | ||
| torch.cuda.empty_cache() | ||
| elif device == "xpu": | ||
| torch.xpu.empty_cache() |
Collaborator
There was a problem hiding this comment.
suggest to use the torch.acc API
liangan1
reviewed
Mar 30, 2026
| # Save model to generated output directory | ||
| print(f"Saving model to {output_dir}...") | ||
| tokenizer.save_pretrained(output_dir) | ||
| print("model:", model) |
Collaborator
There was a problem hiding this comment.
Suggested change
| print("model:", model) |
liangan1
reviewed
Mar 30, 2026
|
|
||
| def main(): | ||
| args = parse_args() | ||
| device = _get_device(args.device) |
Collaborator
There was a problem hiding this comment.
suggest to use torch.acc.get_current_xxx to get the current device information instead of add new params --device. it will change the user behevior
liangan1
reviewed
Mar 30, 2026
|
|
||
| @skip_if_lt_x_gpu(2) | ||
| @unittest.skipIf(not torch.accelerator.is_available(), "Need GPU available") | ||
| @unittest.skipIf(torch.xpu.is_available(), "XPU enablement in progress") |
Collaborator
There was a problem hiding this comment.
pls skip not related UT in another PR.
Contributor
|
this feature is not complete yet, @xiaowangintel @liangan1 can you restrict the contribution only to stable features for now? they are in https://github.com/pytorch/ao/tree/main/torchao/quantization/quantize_ |
Collaborator
Sure. Thanks for your suggestion. We will focus on these features now. |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Summary
This PR enables GPTQ support on Intel GPU.
Previously, GPTQ workflows in torchao were primarily validated on CUDA. This PR extends support to XPU.