[quant][pt2e][xnnpack] Add support for QAT dynamic quantization for linear in XNNPACKQuantizer #113288
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
…for linear in XNNPACKQuantizer Summary: att Test Plan: python test/test_quantization.py TestXNNPACKQuantizer.test_qat_dynamic_linear Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/113288
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit be173fa with merge base 4cb7dd0 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
@jerryzh168 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
…antization for linear in XNNPACKQuantizer" Summary: att Test Plan: python test/test_quantization.py TestXNNPACKQuantizer.test_qat_dynamic_linear Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D51124725](https://our.internmc.facebook.com/intern/diff/D51124725) [ghstack-poisoned]
jerryzh168
changed the title
kimishpatel
requested changes
Nov 30, 2023
…ation for linear in XNNPACKQuantizer" Summary: att Test Plan: python test/test_quantization.py TestXNNPACKQuantizer.test_qat_dynamic_linear Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D51124725](https://our.internmc.facebook.com/intern/diff/D51124725) [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 30, 2023
…inear in XNNPACKQuantizer Summary: FX graph mode quant workflow and also pt2e flow relies on the `is_dynamic` flag in observer/quantizationspec to convert an observer to dynamic quantization patterns (choose_qparams -> q -> dq), this PR added is_dynamic flag for all observers so that it's possible to convert these observers to the pattern. However, this dyanmic quantization pattern is actually only valid for MovingAverageObserver(averaging_constant=1) for the computation before convert and after convert to match in the context of QAT. So we'll have some sanity checks in other observers to make sure the is_dynamic is False. Test Plan: python test/test_quantization.py TestXNNPACKQuantizer.test_qat_dynamic_linear Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: babea59 Pull Request resolved: #113288
…ation for linear in XNNPACKQuantizer" Summary: FX graph mode quant workflow and also pt2e flow relies on the `is_dynamic` flag in observer/quantizationspec to convert an observer to dynamic quantization patterns (choose_qparams -> q -> dq), this PR added is_dynamic flag for all observers so that it's possible to convert these observers to the pattern. However, this dyanmic quantization pattern is actually only valid for MovingAverageObserver(averaging_constant=1) for the computation before convert and after convert to match in the context of QAT. So we'll have some sanity checks in other observers to make sure the is_dynamic is False. Test Plan: python test/test_quantization.py TestXNNPACKQuantizer.test_qat_dynamic_linear Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D51124725](https://our.internmc.facebook.com/intern/diff/D51124725) [ghstack-poisoned]
yeah sure, just added. |
…ation for linear in XNNPACKQuantizer" Summary: FX graph mode quant workflow and also pt2e flow relies on the `is_dynamic` flag in observer/quantizationspec to convert an observer to dynamic quantization patterns (choose_qparams -> q -> dq), this PR added is_dynamic flag for all observers so that it's possible to convert these observers to the pattern. However, this dynamic quantization pattern (choose_qparams -> q -> dq) is actually only valid for MovingAverageObserver(averaging_constant=1) for the computation before convert and after convert to match in the context of QAT. So we'll have some sanity checks in other observers to make sure the is_dynamic is False. Test Plan: python test/test_quantization.py TestXNNPACKQuantizer.test_qat_dynamic_linear Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D51124725](https://our.internmc.facebook.com/intern/diff/D51124725) [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 30, 2023
…inear in XNNPACKQuantizer Summary: FX graph mode quant workflow and also pt2e flow relies on the `is_dynamic` flag in observer/quantizationspec to convert an observer to dynamic quantization patterns (choose_qparams -> q -> dq), this PR added is_dynamic flag for all observers so that it's possible to convert these observers to the pattern. However, this dyanmic quantization pattern is actually only valid for MovingAverageObserver(averaging_constant=1) for the computation before convert and after convert to match in the context of QAT. So we'll have some sanity checks in other observers to make sure the is_dynamic is False. Test Plan: python test/test_quantization.py TestXNNPACKQuantizer.test_qat_dynamic_linear Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 1900c0c Pull Request resolved: #113288
kimishpatel
approved these changes
Dec 1, 2023
…ation for linear in XNNPACKQuantizer" Summary: FX graph mode quant workflow and also pt2e flow relies on the `is_dynamic` flag in observer/quantizationspec to convert an observer to dynamic quantization patterns (choose_qparams -> q -> dq), this PR added is_dynamic flag for all observers so that it's possible to convert these observers to the pattern. However, this dynamic quantization pattern (choose_qparams -> q -> dq) is actually only valid for MovingAverageObserver(averaging_constant=1) for the computation before convert and after convert to match in the context of QAT. So we'll have some sanity checks in other observers to make sure the is_dynamic is False. Test Plan: python test/test_quantization.py TestXNNPACKQuantizer.test_qat_dynamic_linear Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D51124725](https://our.internmc.facebook.com/intern/diff/D51124725) [ghstack-poisoned]
…ation for linear in XNNPACKQuantizer" Summary: FX graph mode quant workflow and also pt2e flow relies on the `is_dynamic` flag in observer/quantizationspec to convert an observer to dynamic quantization patterns (choose_qparams -> q -> dq), this PR added is_dynamic flag for all observers so that it's possible to convert these observers to the pattern. However, this dynamic quantization pattern (choose_qparams -> q -> dq) is actually only valid for MovingAverageObserver(averaging_constant=1) for the computation before convert and after convert to match in the context of QAT. So we'll have some sanity checks in other observers to make sure the is_dynamic is False. Test Plan: python test/test_quantization.py TestXNNPACKQuantizer.test_qat_dynamic_linear Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D51124725](https://our.internmc.facebook.com/intern/diff/D51124725) [ghstack-poisoned]
…ation for linear in XNNPACKQuantizer" Summary: FX graph mode quant workflow and also pt2e flow relies on the `is_dynamic` flag in observer/quantizationspec to convert an observer to dynamic quantization patterns (choose_qparams -> q -> dq), this PR added is_dynamic flag for all observers so that it's possible to convert these observers to the pattern. However, this dynamic quantization pattern (choose_qparams -> q -> dq) is actually only valid for MovingAverageObserver(averaging_constant=1) for the computation before convert and after convert to match in the context of QAT. So we'll have some sanity checks in other observers to make sure the is_dynamic is False. Test Plan: python test/test_quantization.py TestXNNPACKQuantizer.test_qat_dynamic_linear Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D51124725](https://our.internmc.facebook.com/intern/diff/D51124725) [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Dec 2, 2023
…inear in XNNPACKQuantizer Summary: FX graph mode quant workflow and also pt2e flow relies on the `is_dynamic` flag in observer/quantizationspec to convert an observer to dynamic quantization patterns (choose_qparams -> q -> dq), this PR added is_dynamic flag for all observers so that it's possible to convert these observers to the pattern. However, this dyanmic quantization pattern is actually only valid for MovingAverageObserver(averaging_constant=1) for the computation before convert and after convert to match in the context of QAT. So we'll have some sanity checks in other observers to make sure the is_dynamic is False. Test Plan: python test/test_quantization.py TestXNNPACKQuantizer.test_qat_dynamic_linear Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 2497cbb Pull Request resolved: #113288
…ation for linear in XNNPACKQuantizer" Summary: FX graph mode quant workflow and also pt2e flow relies on the `is_dynamic` flag in observer/quantizationspec to convert an observer to dynamic quantization patterns (choose_qparams -> q -> dq), this PR added is_dynamic flag for all observers so that it's possible to convert these observers to the pattern. However, this dynamic quantization pattern (choose_qparams -> q -> dq) is actually only valid for MovingAverageObserver(averaging_constant=1) for the computation before convert and after convert to match in the context of QAT. So we'll have some sanity checks in other observers to make sure the is_dynamic is False. Test Plan: python test/test_quantization.py TestXNNPACKQuantizer.test_qat_dynamic_linear Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D51124725](https://our.internmc.facebook.com/intern/diff/D51124725) [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Dec 4, 2023
…inear in XNNPACKQuantizer Summary: FX graph mode quant workflow and also pt2e flow relies on the `is_dynamic` flag in observer/quantizationspec to convert an observer to dynamic quantization patterns (choose_qparams -> q -> dq), this PR added is_dynamic flag for all observers so that it's possible to convert these observers to the pattern. However, this dyanmic quantization pattern is actually only valid for MovingAverageObserver(averaging_constant=1) for the computation before convert and after convert to match in the context of QAT. So we'll have some sanity checks in other observers to make sure the is_dynamic is False. Test Plan: python test/test_quantization.py TestXNNPACKQuantizer.test_qat_dynamic_linear Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 552fb1a Pull Request resolved: #113288
|
@jerryzh168 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 |
dmenig
pushed a commit
to dmenig/pytorch
that referenced
this pull request
Dec 21, 2023
…inear in XNNPACKQuantizer (pytorch#113288) Summary: FX graph mode quant workflow and also pt2e flow relies on the `is_dynamic` flag in observer/quantizationspec to convert an observer to dynamic quantization patterns (choose_qparams -> q -> dq), this PR added is_dynamic flag for all observers so that it's possible to convert these observers to the pattern. However, this dynamic quantization pattern (choose_qparams -> q -> dq) is actually only valid for MovingAverageObserver(averaging_constant=1) for the computation before convert and after convert to match in the context of QAT. So we'll have some sanity checks in other observers to make sure the is_dynamic is False. Test Plan: python test/test_quantization.py TestXNNPACKQuantizer.test_qat_dynamic_linear Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D51124725](https://our.internmc.facebook.com/intern/diff/D51124725) Pull Request resolved: pytorch#113288 Approved by: https://github.com/kimishpatel
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:
FX graph mode quant workflow and also pt2e flow relies on the
is_dynamicflag in observer/quantizationspec toconvert an observer to dynamic quantization patterns (choose_qparams -> q -> dq), this PR added is_dynamic flag
for all observers so that it's possible to convert these observers to the pattern.
However, this dynamic quantization pattern (choose_qparams -> q -> dq) is actually only valid for MovingAverageObserver(averaging_constant=1)
for the computation before convert and after convert to match in the context of QAT. So we'll have some sanity
checks in other observers to make sure the is_dynamic is False.
Test Plan:
python test/test_quantization.py TestXNNPACKQuantizer.test_qat_dynamic_linear
Reviewers:
Subscribers:
Tasks:
Tags:
Differential Revision: D51124725