Add support to call unpack for pytorch mobile quantized FC and Conv#26211
Closed
supriyar wants to merge 15 commits intogh/supriyar/16/basefrom
Closed
Add support to call unpack for pytorch mobile quantized FC and Conv#26211supriyar wants to merge 15 commits intogh/supriyar/16/basefrom
supriyar wants to merge 15 commits intogh/supriyar/16/basefrom
Conversation
Summary: Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Reviewers: Subscribers: Tasks: Tags:
This was referenced Sep 13, 2019
… and Conv" Summary: Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Reviewers: Subscribers: Tasks: Tags:
… and Conv" Summary: Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Reviewers: Subscribers: Tasks: Tags:
supriyar
added a commit
that referenced
this pull request
Sep 13, 2019
Summary: Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: efdf239 Pull Request resolved: #26211
… and Conv" Summary: Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Reviewers: Subscribers: Tasks: Tags:
supriyar
added a commit
that referenced
this pull request
Sep 15, 2019
Summary: Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: c823250 Pull Request resolved: #26211
dzhulgakov
approved these changes
Sep 15, 2019
Collaborator
dzhulgakov
left a comment
There was a problem hiding this comment.
Looks good, but please add a comment
… and Conv" Summary: Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Reviewers: Subscribers: Tasks: Tags:
supriyar
added a commit
that referenced
this pull request
Sep 16, 2019
Summary: Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 12d941f Pull Request resolved: #26211
… and Conv" Summary: Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
… and Conv" Summary: Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
… and Conv" Summary: Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D17422827](https://our.internmc.facebook.com/intern/diff/D17422827) [ghstack-poisoned]
… and Conv" Summary: Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D17422827](https://our.internmc.facebook.com/intern/diff/D17422827) [ghstack-poisoned]
… and Conv" Summary: Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D17422827](https://our.internmc.facebook.com/intern/diff/D17422827) [ghstack-poisoned]
… and Conv" Summary: Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D17422827](https://our.internmc.facebook.com/intern/diff/D17422827) [ghstack-poisoned]
… and Conv" Summary: Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D17422827](https://our.internmc.facebook.com/intern/diff/D17422827) [ghstack-poisoned]
… and Conv" Summary: Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D17422827](https://our.internmc.facebook.com/intern/diff/D17422827) [ghstack-poisoned]
… and Conv" Summary: Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D17464430](https://our.internmc.facebook.com/intern/diff/D17464430) [ghstack-poisoned]
… and Conv" Summary: Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D17464430](https://our.internmc.facebook.com/intern/diff/D17464430) [ghstack-poisoned]
zdevito
pushed a commit
to zdevito/ATen
that referenced
this pull request
Sep 19, 2019
…#26211) Summary: Pull Request resolved: pytorch/pytorch#26211 Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Imported from OSS Differential Revision: D17464430 fbshipit-source-id: 83ad5a2556dcf13245a1047feef6cfb489c9ef69
Contributor
|
This pull request has been merged in d46b982. |
laurentdupin
pushed a commit
to laurentdupin/pytorch
that referenced
this pull request
Apr 24, 2026
…ytorch#26211) Summary: Pull Request resolved: pytorch#26211 Currently QNNPACK does not have an unpack function like FBGEMM does. In order to be able to script quantized models for mobile, we need to save unpacked weights. This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called Test Plan: python test/test_quantized.py TestQNNPackOps.test_qconv_unpack python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack Imported from OSS Differential Revision: D17464430 fbshipit-source-id: 83ad5a2556dcf13245a1047feef6cfb489c9ef69
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 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.
Stack from ghstack:
Summary:
Currently QNNPACK does not have an unpack function like FBGEMM does.
In order to be able to script quantized models for mobile, we need to save unpacked weights.
This change stores the original weights and bias in the opaque struct and simply returns it when unpack is called
Test Plan:
python test/test_quantized.py TestQNNPackOps.test_qconv_unpack
python test/test_quantized.py TestQNNPackOps.test_qlinear_unpack
Reviewers:
Subscribers:
Tasks:
Tags:
Differential Revision: D17464430