| CARVIEW |
Navigation Menu
-
Notifications
You must be signed in to change notification settings - Fork 24.7k
[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.
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
Conversation
pytorch-bot
bot
added
release notes: quantization
🔗 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 SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 1 New FailureAs of commit 4884bc5 with merge base 081c168 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
This pull request was exported from Phabricator. 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
18404c0 to
2fd9c0f
Compare
|
This pull request was exported from Phabricator. Differential Revision: D65989599 |
mcr229
force-pushed
the
export-D65989599
branch
from
2fd9c0f to
6893e84
Compare
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
|
This pull request was exported from Phabricator. Differential Revision: D65989599 |
…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
mcr229
force-pushed
the
export-D65989599
branch
from
6893e84 to
4884bc5
Compare
|
This pull request was exported from Phabricator. Differential Revision: D65989599 |
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
10 similar comments
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
8 similar comments
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
|
@pytorchbot merge -i (Initiating merge automatically since Phabricator Diff has merged, merging with -i because oss signals were bypassed internally) |
Merge startedYour 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 |
…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
…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
…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
…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
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