[ET-VK][AOT] Enable exporting Q8 Quantized Linear + Convolution #13818
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
As title. Introduce fusion patterns to enable fusing quantized convolution and linear graph patterns into a custom op. ## Changes Introduce the concept of using custom pattern detection functions to detect graph patterns rather than solely relying on SubgraphMatcher. The issue with SubgraphMatcher is that a large number of graph patterns may need to be exported to obtain variants for different combinations of decompositions/quantization workflows. Having a custom detection function improves maintainability. Implement detection + replacement functions for quantized linear and quantized conv2d. Differential Revision: [D81323425](https://our.internmc.facebook.com/intern/diff/D81323425/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13818
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit 023a329 with merge base 1a7441f ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
SS-JIA
pushed a commit
that referenced
this pull request
Aug 29, 2025
As title. Introduce fusion patterns to enable fusing quantized convolution and linear graph patterns into a custom op. ## Changes Introduce the concept of using custom pattern detection functions to detect graph patterns rather than solely relying on SubgraphMatcher. The issue with SubgraphMatcher is that a large number of graph patterns may need to be exported to obtain variants for different combinations of decompositions/quantization workflows. Having a custom detection function improves maintainability. Implement detection + replacement functions for quantized linear and quantized conv2d. Differential Revision: [D81323425](https://our.internmc.facebook.com/intern/diff/D81323425/) ghstack-source-id: 306522052 Pull Request resolved: #13818
This PR needs a
|
meta-cla
bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D81323425 |
…ution" As title. Introduce fusion patterns to enable fusing quantized convolution and linear graph patterns into a custom op. ## Changes Introduce the concept of using custom pattern detection functions to detect graph patterns rather than solely relying on SubgraphMatcher. The issue with SubgraphMatcher is that a large number of graph patterns may need to be exported to obtain variants for different combinations of decompositions/quantization workflows. Having a custom detection function improves maintainability. Implement detection + replacement functions for quantized linear and quantized conv2d. Differential Revision: [D81323425](https://our.internmc.facebook.com/intern/diff/D81323425/) [ghstack-poisoned]
SS-JIA
pushed a commit
that referenced
this pull request
Aug 29, 2025
Pull Request resolved: #13818 As title. Introduce fusion patterns to enable fusing quantized convolution and linear graph patterns into a custom op. ## Changes Introduce the concept of using custom pattern detection functions to detect graph patterns rather than solely relying on SubgraphMatcher. The issue with SubgraphMatcher is that a large number of graph patterns may need to be exported to obtain variants for different combinations of decompositions/quantization workflows. Having a custom detection function improves maintainability. Implement detection + replacement functions for quantized linear and quantized conv2d. ghstack-source-id: 306534857 @exported-using-ghexport Differential Revision: [D81323425](https://our.internmc.facebook.com/intern/diff/D81323425/)
|
This pull request was exported from Phabricator. Differential Revision: D81323425 |
…ution" As title. Introduce fusion patterns to enable fusing quantized convolution and linear graph patterns into a custom op. ## Changes Introduce the concept of using custom pattern detection functions to detect graph patterns rather than solely relying on SubgraphMatcher. The issue with SubgraphMatcher is that a large number of graph patterns may need to be exported to obtain variants for different combinations of decompositions/quantization workflows. Having a custom detection function improves maintainability. Implement detection + replacement functions for quantized linear and quantized conv2d. Differential Revision: [D81323425](https://our.internmc.facebook.com/intern/diff/D81323425/) [ghstack-poisoned]
SS-JIA
pushed a commit
that referenced
this pull request
Aug 29, 2025
Pull Request resolved: #13818 As title. Introduce fusion patterns to enable fusing quantized convolution and linear graph patterns into a custom op. ## Changes Introduce the concept of using custom pattern detection functions to detect graph patterns rather than solely relying on SubgraphMatcher. The issue with SubgraphMatcher is that a large number of graph patterns may need to be exported to obtain variants for different combinations of decompositions/quantization workflows. Having a custom detection function improves maintainability. Implement detection + replacement functions for quantized linear and quantized conv2d. ghstack-source-id: 306547597 @exported-using-ghexport Differential Revision: [D81323425](https://our.internmc.facebook.com/intern/diff/D81323425/)
|
This pull request was exported from Phabricator. Differential Revision: D81323425 |
…ution" As title. Introduce fusion patterns to enable fusing quantized convolution and linear graph patterns into a custom op. ## Changes Introduce the concept of using custom pattern detection functions to detect graph patterns rather than solely relying on SubgraphMatcher. The issue with SubgraphMatcher is that a large number of graph patterns may need to be exported to obtain variants for different combinations of decompositions/quantization workflows. Having a custom detection function improves maintainability. Implement detection + replacement functions for quantized linear and quantized conv2d. Differential Revision: [D81323425](https://our.internmc.facebook.com/intern/diff/D81323425/) [ghstack-poisoned]
SS-JIA
pushed a commit
that referenced
this pull request
Aug 30, 2025
Pull Request resolved: #13818 As title. Introduce fusion patterns to enable fusing quantized convolution and linear graph patterns into a custom op. ## Changes Introduce the concept of using custom pattern detection functions to detect graph patterns rather than solely relying on SubgraphMatcher. The issue with SubgraphMatcher is that a large number of graph patterns may need to be exported to obtain variants for different combinations of decompositions/quantization workflows. Having a custom detection function improves maintainability. Implement detection + replacement functions for quantized linear and quantized conv2d. ghstack-source-id: 306632733 @exported-using-ghexport Differential Revision: [D81323425](https://our.internmc.facebook.com/intern/diff/D81323425/)
|
This pull request was exported from Phabricator. Differential Revision: D81323425 |
…ution" As title. Introduce fusion patterns to enable fusing quantized convolution and linear graph patterns into a custom op. ## Changes Introduce the concept of using custom pattern detection functions to detect graph patterns rather than solely relying on SubgraphMatcher. The issue with SubgraphMatcher is that a large number of graph patterns may need to be exported to obtain variants for different combinations of decompositions/quantization workflows. Having a custom detection function improves maintainability. Implement detection + replacement functions for quantized linear and quantized conv2d. Differential Revision: [D81323425](https://our.internmc.facebook.com/intern/diff/D81323425/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D81323425 |
…ution" As title. Introduce fusion patterns to enable fusing quantized convolution and linear graph patterns into a custom op. ## Changes Introduce the concept of using custom pattern detection functions to detect graph patterns rather than solely relying on SubgraphMatcher. The issue with SubgraphMatcher is that a large number of graph patterns may need to be exported to obtain variants for different combinations of decompositions/quantization workflows. Having a custom detection function improves maintainability. Implement detection + replacement functions for quantized linear and quantized conv2d. Differential Revision: [D81323425](https://our.internmc.facebook.com/intern/diff/D81323425/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D81323425 |
…ution" As title. Introduce fusion patterns to enable fusing quantized convolution and linear graph patterns into a custom op. ## Changes Introduce the concept of using custom pattern detection functions to detect graph patterns rather than solely relying on SubgraphMatcher. The issue with SubgraphMatcher is that a large number of graph patterns may need to be exported to obtain variants for different combinations of decompositions/quantization workflows. Having a custom detection function improves maintainability. Implement detection + replacement functions for quantized linear and quantized conv2d. Differential Revision: [D81323425](https://our.internmc.facebook.com/intern/diff/D81323425/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D81323425 |
…ution" As title. Introduce fusion patterns to enable fusing quantized convolution and linear graph patterns into a custom op. ## Changes Introduce the concept of using custom pattern detection functions to detect graph patterns rather than solely relying on SubgraphMatcher. The issue with SubgraphMatcher is that a large number of graph patterns may need to be exported to obtain variants for different combinations of decompositions/quantization workflows. Having a custom detection function improves maintainability. Implement detection + replacement functions for quantized linear and quantized conv2d. Differential Revision: [D81323425](https://our.internmc.facebook.com/intern/diff/D81323425/) [ghstack-poisoned]
This was referenced Sep 5, 2025
|
This pull request was exported from Phabricator. Differential Revision: D81323425 |
manuelcandales
approved these changes
Sep 5, 2025
…ution" As title. Introduce fusion patterns to enable fusing quantized convolution and linear graph patterns into a custom op. ## Changes Introduce the concept of using custom pattern detection functions to detect graph patterns rather than solely relying on SubgraphMatcher. The issue with SubgraphMatcher is that a large number of graph patterns may need to be exported to obtain variants for different combinations of decompositions/quantization workflows. Having a custom detection function improves maintainability. Implement detection + replacement functions for quantized linear and quantized conv2d. Differential Revision: [D81323425](https://our.internmc.facebook.com/intern/diff/D81323425/) [ghstack-poisoned]
…ution" As title. Introduce fusion patterns to enable fusing quantized convolution and linear graph patterns into a custom op. ## Changes Introduce the concept of using custom pattern detection functions to detect graph patterns rather than solely relying on SubgraphMatcher. The issue with SubgraphMatcher is that a large number of graph patterns may need to be exported to obtain variants for different combinations of decompositions/quantization workflows. Having a custom detection function improves maintainability. Implement detection + replacement functions for quantized linear and quantized conv2d. Differential Revision: [D81323425](https://our.internmc.facebook.com/intern/diff/D81323425/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D81323425 |
facebook-github-bot
merged commit e22e56e
into
gh/SS-JIA/318/base
115 of 118 checks passed
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
SS-JIA
pushed a commit
that referenced
this pull request
Sep 8, 2025
Pull Request resolved: #13818 As title. Introduce fusion patterns to enable fusing quantized convolution and linear graph patterns into a custom op. ## Changes Introduce the concept of using custom pattern detection functions to detect graph patterns rather than solely relying on SubgraphMatcher. The issue with SubgraphMatcher is that a large number of graph patterns may need to be exported to obtain variants for different combinations of decompositions/quantization workflows. Having a custom detection function improves maintainability. Implement detection + replacement functions for quantized linear and quantized conv2d. ghstack-source-id: 308092874 @exported-using-ghexport Differential Revision: [D81323425](https://our.internmc.facebook.com/intern/diff/D81323425/)
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 from ghstack (oldest at bottom):
As title. Introduce fusion patterns to enable fusing quantized convolution and linear graph patterns into a custom op.
Changes
Introduce the concept of using custom pattern detection functions to detect graph patterns rather than solely relying on SubgraphMatcher. The issue with SubgraphMatcher is that a large number of graph patterns may need to be exported to obtain variants for different combinations of decompositions/quantization workflows. Having a custom detection function improves maintainability.
Implement detection + replacement functions for quantized linear and quantized conv2d.
Differential Revision: D81323425