Remove Int8DynamicActivationInt4WeightConfig#3884
Conversation
This config was deprecated in favor of Int8DynamicActivationIntxWeightConfig. Remove the class definition, handler, and all references from imports, tests, QAT code, benchmarks, and documentation. Update QAT docs to reference Int4WeightOnlyConfig as the example base config. Co-authored-by: Cursor <cursoragent@cursor.com> [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/3884
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 5 Unrelated FailuresAs of commit cde821b with merge base d4c1ba3 ( NEW FAILURE - The following job has 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. |
| .. code:: py | ||
|
|
||
| from torchao.quantization import quantize_, Int8DynamicActivationInt4WeightConfig | ||
| from torchao.quantization import quantize_, Int4WeightOnlyConfig |
There was a problem hiding this comment.
replacement for this config is Int8DynamicActivationIntxWeightConfig I think, maybe change to that?
|
|
||
| if __name__ == "__main__": | ||
| run_tests() | ||
| # Tests removed: Int8DynamicActivationInt4WeightConfig has been removed. |
There was a problem hiding this comment.
just remove the file?
also cc @Xia-Weiwen we are using Int8DynamicActivationIntxWeightConfig to replace Int8DynamicActivationInt4WeightConfig now, in case you want to keep the CPU version of this config
There was a problem hiding this comment.
Oh, Thanks @jerryzh168 I missed this message. And the DA8W4 workflow is broken on CPU now. I will work on a PR to fix the workflow and add these test cases back.
|
Remember to import this. There were a lot of internal use cases! |
Stack from ghstack (oldest at bottom):
This config was deprecated in favor of Int8DynamicActivationIntxWeightConfig.
Remove the class definition, handler, and all references from imports, tests,
QAT code, benchmarks, and documentation. Update QAT docs to reference
Int4WeightOnlyConfig as the example base config.
Co-authored-by: Cursor cursoragent@cursor.com