This repository was archived by the owner on Jul 1, 2025. It is now read-only.
Add Support for importing quantized linear in FXIRImporter #5622
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
|
This pull request was exported from Phabricator. Differential Revision: D27451237 |
842974287
force-pushed
the
export-D27451237
branch
from
ee4f5fe to
ec77983
Compare
842974287
added a commit
to 842974287/glow
that referenced
this pull request
May 13, 2021
Summary: Pull Request resolved: pytorch/pytorch#57483 Pull Request resolved: pytorch#5622 Quantized linear has packed parameters. We want to unpack it so that it would be easier for graph optimization and importer to deal with the weight and bias. A customized remapping function is used to unpack quantized linear and map it to acc_op.linear. Reviewed By: gcatron, jfix71, khabinov Differential Revision: D27451237 fbshipit-source-id: 18b1836cdee9f2f078d6aaaddd1cb14a7c43890f
|
This pull request was exported from Phabricator. Differential Revision: D27451237 |
842974287
added a commit
to 842974287/glow
that referenced
this pull request
May 13, 2021
Summary: Pull Request resolved: pytorch/pytorch#57483 Pull Request resolved: pytorch#5622 Quantized linear has packed parameters. We want to unpack it so that it would be easier for graph optimization and importer to deal with the weight and bias. A customized remapping function is used to unpack quantized linear and map it to acc_op.linear. Reviewed By: gcatron, jfix71, khabinov Differential Revision: D27451237 fbshipit-source-id: 1640bf3747e6baef03cafc39f6749109e723878a
842974287
force-pushed
the
export-D27451237
branch
from
ec77983 to
36191b5
Compare
|
This pull request was exported from Phabricator. Differential Revision: D27451237 |
842974287
pushed a commit
to 842974287/glow
that referenced
this pull request
May 13, 2021
Summary: Pull Request resolved: pytorch/pytorch#57483 Pull Request resolved: pytorch#5622 Quantized linear has packed parameters. We want to unpack it so that it would be easier for graph optimization and importer to deal with the weight and bias. A customized remapping function is used to unpack quantized linear and map it to acc_op.linear. Differential Revision: D27451237 fbshipit-source-id: 291644983064e877dde1e1348fa3c423a4a9561f
842974287
pushed a commit
to 842974287/glow
that referenced
this pull request
May 13, 2021
Summary: Pull Request resolved: pytorch/pytorch#57483 Pull Request resolved: pytorch#5622 Quantized linear has packed parameters. We want to unpack it so that it would be easier for graph optimization and importer to deal with the weight and bias. A customized remapping function is used to unpack quantized linear and map it to acc_op.linear. Differential Revision: D27451237 fbshipit-source-id: bd6c3af4837890b57b394cae7385e3bdd4aca52b
842974287
pushed a commit
to 842974287/glow
that referenced
this pull request
May 13, 2021
Summary: Pull Request resolved: pytorch/pytorch#57483 Pull Request resolved: pytorch#5622 Quantized linear has packed parameters. We want to unpack it so that it would be easier for graph optimization and importer to deal with the weight and bias. A customized remapping function is used to unpack quantized linear and map it to acc_op.linear. Differential Revision: D27451237 fbshipit-source-id: 6410fa0a3becab1f0162eb847ac8a8f253ccd398
Summary: Pull Request resolved: pytorch/pytorch#57483 Pull Request resolved: pytorch#5622 Quantized linear has packed parameters. We want to unpack it so that it would be easier for graph optimization and importer to deal with the weight and bias. A customized remapping function is used to unpack quantized linear and map it to acc_op.linear. Reviewed By: gcatron, jfix71, khabinov Differential Revision: D27451237 fbshipit-source-id: d8fd32321f6f4450731e32e1f56a91228484a9a4
|
This pull request was exported from Phabricator. Differential Revision: D27451237 |
842974287
force-pushed
the
export-D27451237
branch
from
36191b5 to
4649677
Compare
842974287
added a commit
to 842974287/pytorch
that referenced
this pull request
May 14, 2021
…ytorch#57483) Summary: Pull Request resolved: pytorch#57483 Pull Request resolved: pytorch/glow#5622 Quantized linear has packed parameters. We want to unpack it so that it would be easier for graph optimization and importer to deal with the weight and bias. A customized remapping function is used to unpack quantized linear and map it to acc_op.linear. Test Plan: `buck test glow/fb/fx/nnpi_importer:test_importer` Reviewed By: gcatron, jfix71, khabinov Differential Revision: D27451237 fbshipit-source-id: cbdc0b875ff7425f14f8c59cd7b86eb4145624bc
842974287
pushed a commit
to 842974287/glow
that referenced
this pull request
May 14, 2021
Summary: Pull Request resolved: pytorch/pytorch#57483 Pull Request resolved: pytorch#5622 Quantized linear has packed parameters. We want to unpack it so that it would be easier for graph optimization and importer to deal with the weight and bias. A customized remapping function is used to unpack quantized linear and map it to acc_op.linear. Differential Revision: D27451237 fbshipit-source-id: b707f491efdf7e7b09b8e9fd052f0b8d4b6c5536
842974287
pushed a commit
to 842974287/pytorch
that referenced
this pull request
May 14, 2021
…ytorch#57483) Summary: Pull Request resolved: pytorch#57483 Pull Request resolved: pytorch/glow#5622 Quantized linear has packed parameters. We want to unpack it so that it would be easier for graph optimization and importer to deal with the weight and bias. A customized remapping function is used to unpack quantized linear and map it to acc_op.linear. Test Plan: `buck test glow/fb/fx/nnpi_importer:test_importer` Differential Revision: D27451237 fbshipit-source-id: f2760ebe84b2afcd4125cc2ed3334bcf6d4fca14
|
This pull request has been merged in 94b78b9. |
facebook-github-bot
pushed a commit
to pytorch/pytorch
that referenced
this pull request
May 15, 2021
…57483) Summary: Pull Request resolved: #57483 Pull Request resolved: pytorch/glow#5622 Quantized linear has packed parameters. We want to unpack it so that it would be easier for graph optimization and importer to deal with the weight and bias. A customized remapping function is used to unpack quantized linear and map it to acc_op.linear. Test Plan: `buck test glow/fb/fx/nnpi_importer:test_importer` Reviewed By: gcatron, jfix71, khabinov Differential Revision: D27451237 fbshipit-source-id: e46e961734788fd5333e227ca6143fd37c33204e
krshrimali
pushed a commit
to krshrimali/pytorch
that referenced
this pull request
May 19, 2021
…ytorch#57483) Summary: Pull Request resolved: pytorch#57483 Pull Request resolved: pytorch/glow#5622 Quantized linear has packed parameters. We want to unpack it so that it would be easier for graph optimization and importer to deal with the weight and bias. A customized remapping function is used to unpack quantized linear and map it to acc_op.linear. Test Plan: `buck test glow/fb/fx/nnpi_importer:test_importer` Reviewed By: gcatron, jfix71, khabinov Differential Revision: D27451237 fbshipit-source-id: e46e961734788fd5333e227ca6143fd37c33204e
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
2 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: Quantized linear has packed parameters. We want to unpack it so that it would be easier for graph optimization and importer to deal with the weight and bias. A customized remapping function is used to unpack quantized linear and map it to acc_op.linear.
Differential Revision: D27451237