[Reopen] [Intel GPU] Set higher tolerance for some models only on XPU Device

[retonym]

Reopen the previous stale closed PR #134192

We need to increase the tolerance slightly to ensure that certain models pass accuracy check on the XPU device.
This pull request preserves the original tolerance threshold for the CUDA device and introduces a new key higher_fp16_bf16_xpu, which only impacts the XPU device.

cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @chenyang78 @kadeng @chauhang @amjames

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/144756

• 📄 Preview Python docs built from this PR
• 📄 Preview C++ docs built from this PR
• ❓ Need help or want to give feedback on the CI? Visit the bot commands wiki or our office hours

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit 76195b4 with merge base b4cee2b ():
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[retonym]

@EikanWang please help to review this reopened PR. Previous PR #134192 with same change is closed due to stale status

[EikanWang]

Suggested change

	def xpu_higher_tolerance(self, current_device, name):
	return (
	current_device == "xpu" and name in self._tolerance["higher_fp16_bf16_xpu"]
	)
	def xpu_higher_tolerance(self, current_device):
	return self._tolerance["higher_fp16_bf16_xpu"] if current_device == "xpu" else []

[retonym]

Thanks for the suggestions; the code has been modified accordingly.

[EikanWang]

Suggested change

	if name in self._tolerance["higher_fp16"] or self.xpu_higher_tolerance(
	current_device, name
	):
	if name in self._tolerance["higher_fp16"] + self.xpu_higher_tolerance(current_device):

[EikanWang]

Suggested change

	if name in self._tolerance["higher_bf16"] or self.xpu_higher_tolerance(
	current_device, name
	):
	if name in self._tolerance["higher_bf16"] + self.xpu_higher_tolerance(current_device):

[retonym]

@pytorchbot rebase

[pytorchmergebot]

@pytorchbot started a rebase job onto refs/remotes/origin/viable/strict. Check the current status here

[pytorchmergebot]

Successfully rebased yunfei/xpu_tolerance onto refs/remotes/origin/viable/strict, please pull locally before adding more changes (for example, via git checkout yunfei/xpu_tolerance && git pull --rebase)

[retonym]

@pytorchbot rebase

[pytorchmergebot]

@pytorchbot started a rebase job onto refs/remotes/origin/viable/strict. Check the current status here

[pytorchmergebot]

Tried to rebase and push PR #144756, but it was already up to date. Try rebasing against main by issuing:
@pytorchbot rebase -b main

[retonym]

@desertfire @EikanWang Could you please help review and merge this PR? It introduces a tolerance setting for the XPU device in the Dynamo benchmark test.

[jianyizh]

@pytorchbot rebase

[pytorchmergebot]

@pytorchbot started a rebase job onto refs/remotes/origin/viable/strict. Check the current status here

[pytorchmergebot]

Successfully rebased yunfei/xpu_tolerance onto refs/remotes/origin/viable/strict, please pull locally before adding more changes (for example, via git checkout yunfei/xpu_tolerance && git pull --rebase)

[EikanWang]

@pytorchbot rebase -b main

[pytorchmergebot]

@pytorchbot started a rebase job onto refs/remotes/origin/main. Check the current status here

[pytorchmergebot]

Successfully rebased yunfei/xpu_tolerance onto refs/remotes/origin/main, please pull locally before adding more changes (for example, via git checkout yunfei/xpu_tolerance && git pull --rebase)

[EikanWang]

@pytorchbot merge

[pytorchmergebot]

Merge started

Your change will be merged once all checks pass (ETA 0-4 Hours).

Learn more about merging in the wiki.

Questions? Feedback? Please reach out to the PyTorch DevX Team

Advanced Debugging

Check the merge workflow status
here

[malfet]

@pytorchbot revert -m "Broke rocm torch bench runs with TypeError: unsupported operand type(s) for |: 'set' and 'list'" -c nosignal

[pytorchmergebot]

@pytorchbot successfully started a revert job. Check the current status here.
Questions? Feedback? Please reach out to the PyTorch DevX Team

[pytorchmergebot]

@retonym your PR has been successfully reverted.

This PR was reopened (likely due to being reverted), so your approval was removed. Please request another review.

[github-actions]

Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as Stale.
Feel free to remove the Stale label if you feel this was a mistake.
If you are unable to remove the Stale label please contact a maintainer in order to do so.
If you want the bot to never mark this PR stale again, add the no-stale label.
Stale pull requests will automatically be closed after 30 days of inactivity.