[Quantized DeConv Support] Dynamically Quantized Deconvolutions with groups ==1 #11864
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
…ups==1 Pull Request resolved: #11730 Supporting Quantized Transposed Convs with Groups being 1. Previously, There was some added support for Quantized Transposed Convolutions but only when the channel axis is 1 and when the groups is 1. The current Quantizer didn't support this because it only allows quantizaing along the zero dim, which is generally the output channels. However for TransposedConvs, the dimension of the weights are: ``` [in_channels, out_channels/groups, h, w] ``` Since we want to keep quantization along the output channels, we now need to quantize along axis = 1. The reason we require groups to be one is because XNNPACK takes in filters of the dimension: ``` [out_channels, H, W, in_channels/groups] ``` Since we are quantizing along the output channels, in pytorch we expect to have out_channels/groups scales, but in xnnpack we have out_channels scales! Realistically we would need to support this with some affine quantization, where we provide a scale for every group, every out_channel. However for now, we just ensure the constraint where groups == 1. ghstack-source-id: 291033630 @exported-using-ghexport Differential Revision: [D76631781](https://our.internmc.facebook.com/intern/diff/D76631781/)
…groups ==1 Pull Request resolved: #11731 Here we support dynamically quantized Deconvolutions. There is some refactoring of the previous diff, but in general, we just remove the constraint in the Dynamism check that the convolution isn't transposed. For the same reasons as before, this only supports channel_axis = 1 and groups = 1. ghstack-source-id: 291033632 @exported-using-ghexport Differential Revision: [D76638904](https://our.internmc.facebook.com/intern/diff/D76638904/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11864
Note: Links to docs will display an error until the docs builds have been completed. ❌ 4 New Failures, 3 Unrelated FailuresAs of commit 6481220 with merge base 057558f ( NEW FAILURES - The following jobs have failed:
FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
This PR needs a
|
digantdesai
approved these changes
Jul 11, 2025
| if ( | ||
| # skip if transposed conv has more than 1 group | ||
| skip = skip or (is_conv_transpose and num_groups != 1) | ||
| print(f"{skip} conv transpose and num_groups") |
| self._test( | ||
| PerChannelConvTranspose2d( | ||
| 3 * groups, 5 * groups, groups, ch_axis | ||
| ), # ch_axis=0 |
|
|
||
| if is_conv_transpose: | ||
| # transposed convs per output channel quantization | ||
| weight_qspec = change_quantization_config(weight_qspec, ch_axis=1) |
There was a problem hiding this comment.
Do we support group > 1 here in the quant flow? I know we are checking above but just curious. If yes, we can move this before the group check, if not then add an assert to avoid future issues when we allow groups > 1 for transposed_conv.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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
I believe I prematurely merged #11775 and messed up the ghstack. There is no PR for #11731. .github/scripts/propose_ghstack_orig_pr.py is erroring out with a validation error (422?) so I'm attempting to manually create the PR to fix this.
@diff-train-skip-merge
Test plan
CI