Use fbgemm for quantize/dequantize ops
#19500
Closed
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 3 commits
April 19, 2019 10:47
Differential Revision: D15014561 Differential Version: 80114220
Differential Revision: D15014561 Differential Version: 80202432
Differential Revision: D15014561 Differential Version: 80202583
ezyang
reviewed
Apr 22, 2019
| tensor.options().dtype(at::kQInt8), | ||
| intrusive_from_this()); | ||
| auto qvd = qv.data<qint8>(); | ||
| tensor.contiguous(); |
There was a problem hiding this comment.
Nice catch. Would be good to have a test for this case.
|
Change looks fine to me. Resigning in favor of other reviewers. |
|
Is FBGEMM codepath being exercised in CI? What about the non-FBGEMM codepath? |
Differential Revision: D15014561 Differential Version: 80387485
I am not sure if CI sets the |
|
This pull request has been merged in 3cc60e5. |
zdevito
pushed a commit
to zdevito/ATen
that referenced
this pull request
Apr 23, 2019
Summary: Pull Request resolved: pytorch/pytorch#19500 Changes the `quantize_linear` and `dequantize` to `fbgemm`-based implementation. Reviewed By: jianyuh, jerryzh168 Differential Revision: D15014561 fbshipit-source-id: b651e69d336b5b08b4a75a4a4eddf46c040a4934
zhangguanheng66
pushed a commit
to zhangguanheng66/pytorch
that referenced
this pull request
May 6, 2019
Summary: Pull Request resolved: pytorch#19500 Changes the `quantize_linear` and `dequantize` to `fbgemm`-based implementation. Reviewed By: jianyuh, jerryzh168 Differential Revision: D15014561 fbshipit-source-id: b651e69d336b5b08b4a75a4a4eddf46c040a4934
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Outdated suggestions cannot be applied.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.
Stack:
:black_circle: #19500 Use
fbgemmfor quantize/dequantize ops 💚Changes the
quantize_linearanddequantizetofbgemm-based implementation.Differential Revision: D15014561