Fix ReLU fusion when conv/linear has > 1 user #6894
Merged
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/pytorch/executorch/6894
Note: Links to docs will display an error until the docs builds have been completed. ❗ 2 Active SEVsThere are 2 currently active SEVs. If your PR is affected, please view them below:
✅ No FailuresAs of commit 84cf62e with merge base 5b4d9bb ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D65989599 |
mcr229
force-pushed
the
export-D65989599
branch
from
91b798d to
40e0d2a
Compare
mcr229
added a commit
to mcr229/executorch
that referenced
this pull request
Nov 15, 2024
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
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D65989599 |
mcr229
force-pushed
the
export-D65989599
branch
from
40e0d2a to
aa3cf7c
Compare
mcr229
added a commit
to mcr229/executorch
that referenced
this pull request
Nov 18, 2024
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
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
force-pushed
the
export-D65989599
branch
from
aa3cf7c to
84cf62e
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D65989599 |
1 similar comment
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D65989599 |
mcr229
added a commit
to mcr229/pytorch
that referenced
this pull request
Nov 18, 2024
…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
digantdesai
approved these changes
Nov 18, 2024
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:
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