[quant][pt2] Support conv1d-bn QAT fusion #113714
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
Summary: Previously the PT2 QAT code only supported conv2d-bn. This commit extends all existing QAT fusion support to conv1d-bn, including support for all variants like relu, no bias, literal args, cuda etc. This commit also refactors the code such that we can support conv3d-bn easily in the future. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d Reviewers: jerryzh168, kimishpatel Subscribers: jerryzh168, kimishpatel, supriyar [ghstack-poisoned]
This was referenced Nov 14, 2023
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/113714
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 7e422ed with merge base 4f8cb52 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
Summary: Previously the PT2 QAT code only supported conv2d-bn. This commit extends all existing QAT fusion support to conv1d-bn, including support for all variants like relu, no bias, literal args, cuda etc. This commit also refactors the code such that we can support conv3d-bn easily in the future. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d Reviewers: jerryzh168, kimishpatel Subscribers: jerryzh168, kimishpatel, supriyar [ghstack-poisoned]
andrewor14
added a commit
that referenced
this pull request
Nov 14, 2023
Summary: Previously the PT2 QAT code only supported conv2d-bn. This commit extends all existing QAT fusion support to conv1d-bn, including support for all variants like relu, no bias, literal args, cuda etc. This commit also refactors the code such that we can support conv3d-bn easily in the future. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d Reviewers: jerryzh168, kimishpatel Subscribers: jerryzh168, kimishpatel, supriyar ghstack-source-id: 5012aae Pull Request resolved: #113714
jerryzh168
reviewed
Nov 15, 2023
jerryzh168
reviewed
Nov 15, 2023
jerryzh168
reviewed
Nov 15, 2023
jerryzh168
approved these changes
Nov 15, 2023
Summary: Previously the PT2 QAT code only supported conv2d-bn. This commit extends all existing QAT fusion support to conv1d-bn, including support for all variants like relu, no bias, literal args, cuda etc. This commit also refactors the code such that we can support conv3d-bn easily in the future. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d Reviewers: jerryzh168, kimishpatel Subscribers: jerryzh168, kimishpatel, supriyar [ghstack-poisoned]
andrewor14
added a commit
that referenced
this pull request
Nov 15, 2023
Summary: Previously the PT2 QAT code only supported conv2d-bn. This commit extends all existing QAT fusion support to conv1d-bn, including support for all variants like relu, no bias, literal args, cuda etc. This commit also refactors the code such that we can support conv3d-bn easily in the future. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d Reviewers: jerryzh168, kimishpatel Subscribers: jerryzh168, kimishpatel, supriyar ghstack-source-id: ef0ff61 Pull Request resolved: #113714
Summary: Previously the PT2 QAT code only supported conv2d-bn. This commit extends all existing QAT fusion support to conv1d-bn, including support for all variants like relu, no bias, literal args, cuda etc. This commit also refactors the code such that we can support conv3d-bn easily in the future. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d Reviewers: jerryzh168, kimishpatel Subscribers: jerryzh168, kimishpatel, supriyar [ghstack-poisoned]
Summary: Previously the PT2 QAT code only supported conv2d-bn. This commit extends all existing QAT fusion support to conv1d-bn, including support for all variants like relu, no bias, literal args, cuda etc. This commit also refactors the code such that we can support conv3d-bn easily in the future. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d Reviewers: jerryzh168, kimishpatel Subscribers: jerryzh168, kimishpatel, supriyar [ghstack-poisoned]
andrewor14
added a commit
that referenced
this pull request
Nov 15, 2023
Summary: Previously the PT2 QAT code only supported conv2d-bn. This commit extends all existing QAT fusion support to conv1d-bn, including support for all variants like relu, no bias, literal args, cuda etc. This commit also refactors the code such that we can support conv3d-bn easily in the future. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d Reviewers: jerryzh168, kimishpatel Subscribers: jerryzh168, kimishpatel, supriyar ghstack-source-id: 3e0e06a Pull Request resolved: #113714
Summary: Previously the PT2 QAT code only supported conv2d-bn. This commit extends all existing QAT fusion support to conv1d-bn, including support for all variants like relu, no bias, literal args, cuda etc. This commit also refactors the code such that we can support conv3d-bn easily in the future. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d Reviewers: jerryzh168, kimishpatel Subscribers: jerryzh168, kimishpatel, supriyar [ghstack-poisoned]
andrewor14
added a commit
that referenced
this pull request
Nov 15, 2023
Summary: Previously the PT2 QAT code only supported conv2d-bn. This commit extends all existing QAT fusion support to conv1d-bn, including support for all variants like relu, no bias, literal args, cuda etc. This commit also refactors the code such that we can support conv3d-bn easily in the future. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d Reviewers: jerryzh168, kimishpatel Subscribers: jerryzh168, kimishpatel, supriyar ghstack-source-id: 7427648 Pull Request resolved: #113714
Summary: Previously the PT2 QAT code only supported conv2d-bn. This commit extends all existing QAT fusion support to conv1d-bn, including support for all variants like relu, no bias, literal args, cuda etc. This commit also refactors the code such that we can support conv3d-bn easily in the future. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d Reviewers: jerryzh168, kimishpatel Subscribers: jerryzh168, kimishpatel, supriyar [ghstack-poisoned]
andrewor14
added a commit
that referenced
this pull request
Nov 17, 2023
Summary: Previously the PT2 QAT code only supported conv2d-bn. This commit extends all existing QAT fusion support to conv1d-bn, including support for all variants like relu, no bias, literal args, cuda etc. This commit also refactors the code such that we can support conv3d-bn easily in the future. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d Reviewers: jerryzh168, kimishpatel Subscribers: jerryzh168, kimishpatel, supriyar ghstack-source-id: 6298921 Pull Request resolved: #113714
|
@andrewor14 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
|
@andrewor14 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
|
@pytorchbot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
izaitsevfb
added a commit
to pytorch/test-infra
that referenced
this pull request
Nov 21, 2023
This workflow can be used to analyze PR dependencies on demand. It finds: * conflicting commits with the `main` branch, if PR is not mergeable * required commits in the recent history of the PR base The workflow is intended to be run on demand, given the PR url/number. It works for both merged and open PR's, PR doesn't have to be mergeable into `main`. The only limitation is that PR branch has to exist. --- # Testing 1. PR that is not mergeable into the `main` ([#113650](pytorch/pytorch#113650)): https://github.com/pytorch/test-infra/actions/runs/6937037180 3. Dependencies of the GH stack (merged) ([113714](pytorch/pytorch#113714)): https://github.com/pytorch/test-infra/actions/runs/6937145160 --- After addressing review comments, tested end-to-end in a separate repo: * https://github.com/izaitsevfb/pr-head-test/actions/runs/6950229152 * https://github.com/izaitsevfb/pr-head-test/actions/runs/6950296251
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):
Summary: Previously the PT2 QAT code only supported conv2d-bn.
This commit extends all existing QAT fusion support to conv1d-bn,
including support for all variants like relu, no bias, literal
args, cuda etc. This commit also refactors the code such that
we can support conv3d-bn easily in the future.
Test Plan:
python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d
Reviewers: jerryzh168, kimishpatel
Subscribers: jerryzh168, kimishpatel, supriyar
Differential Revision:
Differential Revision: D51428979