Remove old change_linear_weights_to_* APIs#2721
Merged
Merged
Conversation
**Summary:** This commit deprecates the following variables: ``` TORCH_VERSION_AT_LEAST_2_5 TORCH_VERSION_AT_LEAST_2_4 TORCH_VERSION_AT_LEAST_2_3 TORCH_VERSION_AT_LEAST_2_2 TORCH_VERSION_AFTER_2_5 TORCH_VERSION_AFTER_2_4 TORCH_VERSION_AFTER_2_3 TORCH_VERSION_AFTER_2_2 ``` As of this commit, the latest released version of PyTorch is 2.8, which means we can drop support for 2.5 and before since we only support 3 of the latest releases. The next commit will remove usages of all of these variables from within torchao. **Test Plan:** ``` python test/test_utils.py -k torch_version_deprecation ``` [ghstack-poisoned]
**Summary:** This commit deprecates the following variables: ``` TORCH_VERSION_AT_LEAST_2_5 TORCH_VERSION_AT_LEAST_2_4 TORCH_VERSION_AT_LEAST_2_3 TORCH_VERSION_AT_LEAST_2_2 TORCH_VERSION_AFTER_2_5 TORCH_VERSION_AFTER_2_4 TORCH_VERSION_AFTER_2_3 TORCH_VERSION_AFTER_2_2 ``` As of this commit, the latest released version of PyTorch is 2.8, which means we can drop support for 2.5 and before since we only support 3 of the latest releases. The next commit will remove usages of all of these variables from within torchao. **Test Plan:** ``` python test/test_utils.py -k torch_version_deprecation ``` [ghstack-poisoned]
**Summary:** We gate on the PyTorch version throughout the repo. Recently PyTorch 2.8 was released, so the oldest PyTorch version we need to support is 2.6. After this commit, we assume the user is running PyTorch 2.6+, and remove all references to the following variables, which are deprecated. ``` TORCH_VERSION_AT_LEAST_2_6 TORCH_VERSION_AT_LEAST_2_5 TORCH_VERSION_AT_LEAST_2_4 TORCH_VERSION_AT_LEAST_2_3 TORCH_VERSION_AT_LEAST_2_2 TORCH_VERSION_AFTER_2_5 TORCH_VERSION_AFTER_2_4 TORCH_VERSION_AFTER_2_3 TORCH_VERSION_AFTER_2_2 ``` **Test Plan:** CI [ghstack-poisoned]
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2721
Note: Links to docs will display an error until the docs builds have been completed. This comment was automatically generated by Dr. CI and updates every 15 minutes. |
andrewor14
added a commit
that referenced
this pull request
Aug 8, 2025
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI ghstack-source-id: 97b1635 Pull Request resolved: #2721
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
andrewor14
added a commit
that referenced
this pull request
Aug 8, 2025
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI ghstack-source-id: d370c59 Pull Request resolved: #2721
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
andrewor14
added a commit
that referenced
this pull request
Aug 8, 2025
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI ghstack-source-id: ec7860e Pull Request resolved: #2721
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
andrewor14
added a commit
that referenced
this pull request
Aug 8, 2025
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI ghstack-source-id: 7819b42 Pull Request resolved: #2721
jerryzh168
reviewed
Aug 8, 2025
| @@ -120,9 +120,6 @@ | |||
| ZeroPointDomain, | |||
| ) | |||
| from .subclass import ( | |||
Contributor
There was a problem hiding this comment.
this file can be deleted as well?
Contributor
There was a problem hiding this comment.
Contributor
Author
There was a problem hiding this comment.
Looks like classes from this file is still being used in autoquant. I don't think we can delete or even deprecate yet...
Contributor
Author
There was a problem hiding this comment.
Ok, created an issue here instead: #2745. Let's do them separately because there are autoquant/benchmark dependencies
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
andrewor14
added a commit
that referenced
this pull request
Aug 8, 2025
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI ghstack-source-id: 745bf69 Pull Request resolved: #2721
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
jerryzh168
approved these changes
Aug 12, 2025
Contributor
|
BC breaking note? we can direct them to new APIs I think |
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
**Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
liangel-02
pushed a commit
that referenced
this pull request
Aug 25, 2025
* Deprecate old TORCH_VERSION variables **Summary:** This commit deprecates the following variables: ``` TORCH_VERSION_AT_LEAST_2_5 TORCH_VERSION_AT_LEAST_2_4 TORCH_VERSION_AT_LEAST_2_3 TORCH_VERSION_AT_LEAST_2_2 TORCH_VERSION_AFTER_2_5 TORCH_VERSION_AFTER_2_4 TORCH_VERSION_AFTER_2_3 TORCH_VERSION_AFTER_2_2 ``` As of this commit, the latest released version of PyTorch is 2.8, which means we can drop support for 2.5 and before since we only support 3 of the latest releases. The next commit will remove usages of all of these variables from within torchao. **Test Plan:** ``` python test/test_utils.py -k torch_version_deprecation ``` [ghstack-poisoned] * Update on "Deprecate old TORCH_VERSION variables" **Summary:** This commit deprecates the following variables: ``` TORCH_VERSION_AT_LEAST_2_5 TORCH_VERSION_AT_LEAST_2_4 TORCH_VERSION_AT_LEAST_2_3 TORCH_VERSION_AT_LEAST_2_2 TORCH_VERSION_AFTER_2_5 TORCH_VERSION_AFTER_2_4 TORCH_VERSION_AFTER_2_3 TORCH_VERSION_AFTER_2_2 ``` As of this commit, the latest released version of PyTorch is 2.8, which means we can drop support for 2.5 and before since we only support 3 of the latest releases. The next commit will remove usages of all of these variables from within torchao. **Test Plan:** ``` python test/test_utils.py -k torch_version_deprecation ``` [ghstack-poisoned] * Drop support for PyTorch 2.5 and before **Summary:** We gate on the PyTorch version throughout the repo. Recently PyTorch 2.8 was released, so the oldest PyTorch version we need to support is 2.6. After this commit, we assume the user is running PyTorch 2.6+, and remove all references to the following variables, which are deprecated. ``` TORCH_VERSION_AT_LEAST_2_6 TORCH_VERSION_AT_LEAST_2_5 TORCH_VERSION_AT_LEAST_2_4 TORCH_VERSION_AT_LEAST_2_3 TORCH_VERSION_AT_LEAST_2_2 TORCH_VERSION_AFTER_2_5 TORCH_VERSION_AFTER_2_4 TORCH_VERSION_AFTER_2_3 TORCH_VERSION_AFTER_2_2 ``` **Test Plan:** CI [ghstack-poisoned] * Remove old `change_linear_weights_to_*` APIs **Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned] * Update base for Update on "Remove old `change_linear_weights_to_*` APIs" **Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned] * Update base for Update on "Remove old `change_linear_weights_to_*` APIs" **Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned] * Update base for Update on "Remove old `change_linear_weights_to_*` APIs" **Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned] * Update base for Update on "Remove old `change_linear_weights_to_*` APIs" **Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **BC-breaking notes:** Before: ``` change_linear_weights_to_int8_dqtensors(model) change_linear_weights_to_int8_woqtensors(model) change_linear_weights_to_int4_woqtensors(model) ``` After: ``` quantize_(model, Int8WeightOnlyConfig()) quantize_(model, Int4WeightOnlyConfig()) ``` **Test Plan:** CI [ghstack-poisoned] * Update base for Update on "Remove old `change_linear_weights_to_*` APIs" **Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned] * Update base for Update on "Remove old `change_linear_weights_to_*` APIs" **Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned] * Update base for Update on "Remove old `change_linear_weights_to_*` APIs" **Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned] * Update base for Update on "Remove old `change_linear_weights_to_*` APIs" **Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned] * Update base for Update on "Remove old `change_linear_weights_to_*` APIs" **Summary:** This commit removes these super old quantization APIs that aren't even accessible by the user: ``` change_linear_weights_to_int8_dqtensors change_linear_weights_to_int8_woqtensors change_linear_weights_to_int4_woqtensors ``` **Test Plan:** CI [ghstack-poisoned]
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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):
export_for_trainingwithtorch.export.export#2724change_linear_weights_to_*APIs #2721Summary: This commit removes these super old quantization
APIs that aren't even accessible by the user:
BC-breaking notes:
Before:
After:
Test Plan: CI