KEMBAR78
[Quantizer][XNNPACK] Fix ReLU fusion when conv/linear has > 1 user by mcr229 · Pull Request #140846 · pytorch/pytorch · GitHub
Skip to content

[Quantizer][XNNPACK] Fix ReLU fusion when conv/linear has > 1 user #140846

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.

Sign up for GitHub

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

Jump to bottom
Closed
wants to merge 1 commit into from
Closed

[Quantizer][XNNPACK] Fix ReLU fusion when conv/linear has > 1 user #140846

wants to merge 1 commit into from

Conversation

@mcr229
Copy link
Contributor

@mcr229 mcr229 commented Nov 15, 2024

Summary:
Bug in quantizer when Conv + ReLU is fused even when the preceeding conv has more than one user. Conv and ReLU can not be fused in this case because the result of Conv must be used elsewhere.

XNNPACK Delegate naturally handles this by inserting a clamp node for ReLU.

Test Plan: CI

Reviewed By: digantdesai

Differential Revision: D65989599

@pytorch-bot
Copy link

pytorch-bot bot commented Nov 15, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/140846

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

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

❌ 1 New Failure

As of commit 4884bc5 with merge base 081c168 (image):

NEW FAILURE - The following job has failed:

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

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D65989599

mcr229 added a commit to mcr229/executorch that referenced this pull request Nov 15, 2024
@mcr229 @facebook-github-bot
Fix ReLU fusion when conv/linear has > 1 user (pytorch#6894)
40e0d2a 
Summary:
X-link: pytorch/pytorch#140846


Bug in quantizer when Conv + ReLU is fused even when the preceeding conv has more than one user. Conv and ReLU can not be fused in this case because the result of Conv must be used elsewhere.

XNNPACK Delegate naturally handles this by inserting a clamp node for ReLU.

Reviewed By: digantdesai

Differential Revision: D65989599
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D65989599

mcr229 added a commit to mcr229/executorch that referenced this pull request Nov 18, 2024
@mcr229 @facebook-github-bot
Fix ReLU fusion when conv/linear has > 1 user (pytorch#6894)
aa3cf7c 
Summary:
X-link: pytorch/pytorch#140846


Bug in quantizer when Conv + ReLU is fused even when the preceeding conv has more than one user. Conv and ReLU can not be fused in this case because the result of Conv must be used elsewhere.

XNNPACK Delegate naturally handles this by inserting a clamp node for ReLU.

Reviewed By: digantdesai

Differential Revision: D65989599
mcr229 added a commit to mcr229/executorch that referenced this pull request Nov 18, 2024
@mcr229 @facebook-github-bot
Fix ReLU fusion when conv/linear has > 1 user (pytorch#6894)
84cf62e 
Summary:
X-link: pytorch/pytorch#140846


Bug in quantizer when Conv + ReLU is fused even when the preceeding conv has more than one user. Conv and ReLU can not be fused in this case because the result of Conv must be used elsewhere.

XNNPACK Delegate naturally handles this by inserting a clamp node for ReLU.

Reviewed By: digantdesai

Differential Revision: D65989599
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D65989599

@mcr229 @facebook-github-bot
[Quantizer][XNNPACK] Fix ReLU fusion when conv/linear has > 1 user (p…
4884bc5 
…ytorch#140846)

Summary:

X-link: pytorch/executorch#6894

Bug in quantizer when Conv + ReLU is fused even when the preceeding conv has more than one user. Conv and ReLU can not be fused in this case because the result of Conv must be used elsewhere.

XNNPACK Delegate naturally handles this by inserting a clamp node for ReLU.

Test Plan: CI

Reviewed By: digantdesai

Differential Revision: D65989599
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D65989599

@pytorch-bot pytorch-bot bot added the ciflow/trunk Trigger trunk jobs on your pull request label Nov 18, 2024
@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

10 similar comments
@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

8 similar comments
@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

@facebook-github-bot
Copy link
Contributor

@pytorchbot merge -i

(Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally)

@pytorchmergebot
Copy link
Collaborator

Merge started

Your change will be merged while ignoring the following 1 checks: pull / linux-focal-py3.9-clang10-onnx / test (default, 2, 2, lf.linux.2xlarge)

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

pobin6 pushed a commit to pobin6/pytorch that referenced this pull request Dec 5, 2024
@mcr229
[Quantizer][XNNPACK] Fix ReLU fusion when conv/linear has > 1 user (p…
e9d2fb7 
…ytorch#140846)

Summary:
Bug in quantizer when Conv + ReLU is fused even when the preceeding conv has more than one user. Conv and ReLU can not be fused in this case because the result of Conv must be used elsewhere.

XNNPACK Delegate naturally handles this by inserting a clamp node for ReLU.

Test Plan: CI

Reviewed By: digantdesai

Differential Revision: D65989599

Pull Request resolved: pytorch#140846
Approved by: https://github.com/digantdesai
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@digantdesai digantdesai digantdesai approved these changes

Assignees

No one assigned

Labels

ciflow/trunk Trigger trunk jobs on your pull request fb-exported Merged release notes: AO frontend release notes: quantization release notes category

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@mcr229 @facebook-github-bot @pytorchmergebot @digantdesai