[quantization] Store bias in PackedLinearWeight struct in fbgemm #25428
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
Added bias as an optional param to the quantized_linear_prepack function. Bias is quantized during runtime using input scale and weight scale. Differential Revision: [D17121304](https://our.internmc.facebook.com/intern/diff/D17121304/)
pytorchbot
added
oncall: jit
…fbgemm" Added bias as an optional param to the quantized_linear_prepack function. Bias is quantized during runtime using input scale and weight scale. Differential Revision: [D17121304](https://our.internmc.facebook.com/intern/diff/D17121304/)
…fbgemm" Added bias as an optional param to the quantized_linear_prepack function. Bias is quantized during runtime using input scale and weight scale. Differential Revision: [D17121304](https://our.internmc.facebook.com/intern/diff/D17121304/)
supriyar
added a commit
that referenced
this pull request
Aug 30, 2019
Pull Request resolved: #25428 Added bias as an optional param to the quantized_linear_prepack function. Bias is quantized during runtime using input scale and weight scale. ghstack-source-id: 89269220 Differential Revision: [D17121304](https://our.internmc.facebook.com/intern/diff/D17121304/)
This comment has been minimized.
This comment has been minimized.
dzhulgakov
requested changes
Aug 30, 2019
jianyuh
reviewed
Aug 30, 2019
…fbgemm" Added bias as an optional param to the quantized_linear_prepack function. Bias is quantized during runtime using input scale and weight scale. Differential Revision: [D17121304](https://our.internmc.facebook.com/intern/diff/D17121304/)
…fbgemm" Added bias as an optional param to the quantized_linear_prepack function. Bias is quantized during runtime using input scale and weight scale. Differential Revision: [D17121304](https://our.internmc.facebook.com/intern/diff/D17121304/)
jamesr66a
requested changes
Aug 30, 2019
Collaborator
jamesr66a
left a comment
jamesr66a
left a comment
There was a problem hiding this comment.
ROCM failure is true-positive. The function signature at qlinear.cpp:218 needs to be updated
…fbgemm" Added bias as an optional param to the quantized_linear_prepack function. Bias is quantized during runtime using input scale and weight scale. Differential Revision: [D17121304](https://our.internmc.facebook.com/intern/diff/D17121304/)
supriyar
added a commit
that referenced
this pull request
Aug 30, 2019
Pull Request resolved: #25428 Added bias as an optional param to the quantized_linear_prepack function. Bias is quantized during runtime using input scale and weight scale. ghstack-source-id: 89329368 Differential Revision: [D17121304](https://our.internmc.facebook.com/intern/diff/D17121304/)
dzhulgakov
reviewed
Sep 3, 2019
dskhudia
reviewed
Sep 3, 2019
dskhudia
approved these changes
Sep 4, 2019
Contributor
|
I have approved it. Please take care of the tests. |
dskhudia
reviewed
Sep 4, 2019
…fbgemm" Added bias as an optional param to the quantized_linear_prepack function. Bias is quantized during runtime using input scale and weight scale. Differential Revision: [D17121304](https://our.internmc.facebook.com/intern/diff/D17121304/)
| /*ld=*/K, | ||
| /*pmat=*/nullptr, // PackBMatrix manages ownership of pmat | ||
| /*groups=*/1), | ||
| bias_contig, |
Contributor
There was a problem hiding this comment.
How does this work when bias is None?
Contributor
Author
There was a problem hiding this comment.
It is stored as an optional tensor - similar to the current linear op that has bias as an input argument. So if it is none then that gets taken care of.
Contributor
raghuramank100
suggested changes
Sep 4, 2019
Contributor
raghuramank100
left a comment
raghuramank100
left a comment
There was a problem hiding this comment.
Looks great, a few suggested changes.
…fbgemm" Added bias as an optional param to the quantized_linear_prepack function. Bias is quantized during runtime using input scale and weight scale. Differential Revision: [D17121304](https://our.internmc.facebook.com/intern/diff/D17121304/)
…fbgemm" Added bias as an optional param to the quantized_linear_prepack function. Bias is quantized during runtime using input scale and weight scale. Differential Revision: [D17121304](https://our.internmc.facebook.com/intern/diff/D17121304/)
…fbgemm" Added bias as an optional param to the quantized_linear_prepack function. Bias is quantized during runtime using input scale and weight scale. Differential Revision: [D17121304](https://our.internmc.facebook.com/intern/diff/D17121304/)
…fbgemm" Added bias as an optional param to the quantized_linear_prepack function. Bias is quantized during runtime using input scale and weight scale. Differential Revision: [D17121304](https://our.internmc.facebook.com/intern/diff/D17121304/)
Contributor
Author
|
Removed self.bias from the modules. Added |
…fbgemm" Added bias as an optional param to the quantized_linear_prepack function. Bias is quantized during runtime using input scale and weight scale. Differential Revision: [D17121304](https://our.internmc.facebook.com/intern/diff/D17121304/)
Member
The updated API for |
jianyuh
approved these changes
Sep 6, 2019
Contributor
|
This pull request has been merged in 9d2d31e. |
zdevito
pushed a commit
to zdevito/ATen
that referenced
this pull request
Sep 6, 2019
Summary: Pull Request resolved: pytorch/pytorch#25428 Added bias as an optional param to the quantized_linear_prepack function. Bias is quantized during runtime using input scale and weight scale. ghstack-source-id: 89601399 Test Plan: python test/run_test.py --exclude nn --verbose --bring-to-front quantization quantized quantized_tensor quantized_nn_mods quantizer Differential Revision: D17121304 fbshipit-source-id: 8adb0e55e4aed0a5430aaa2c8639c8ad1639c85a
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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:
Added bias as an optional param to the quantized_linear_prepack function.
Bias is quantized during runtime using input scale and weight scale.
Differential Revision: D17121304