[Quant][PT2E]change flatten recipe for X86InductorQuantizer #136298
Closed
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/136298
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (4 Unrelated Failures)As of commit aed4b1d with merge base 0cdc6a8 ( FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
| elif ( | ||
| node.target is torch.ops.aten.flatten.using_ints | ||
| and len(node.users) > 0 | ||
| and not is_any_users_connected_to_quantizable_op(node.users) |
There was a problem hiding this comment.
nit: not any([user for user in list(node.users.keys()) if user.target in quantizable_ops]). since is_any_users_connected_to_quantizable_op is only used here.
There was a problem hiding this comment.
Please also add a comment for the special recipe of flatten here.
|
Thank you for your review. The code and description have been updated. |
leslie-fang-intel
approved these changes
Sep 19, 2024
jgong5
approved these changes
Sep 23, 2024
ViT |
|
@pytorchbot merge |
Merge startedYour 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 |
BoyuanFeng
pushed a commit
to BoyuanFeng/pytorch
that referenced
this pull request
Sep 25, 2024
…136298) This PR modifies the flatten recipe: if none of the users of the flatten node are quantizable ops, int8 flatten will be disabled to avoid unnecessary dtype conversions. Pull Request resolved: pytorch#136298 Approved by: https://github.com/leslie-fang-intel, https://github.com/jgong5
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.
Stack from ghstack (oldest at bottom):
This PR modifies the flatten recipe: if none of the users of the flatten node are quantizable ops, int8 flatten will be disabled to avoid unnecessary dtype conversions.
cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @wenzhe-nrv @jiayisunx @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @ColinPeppler @amjames @desertfire @chauhang