Open
Conversation
Signed-off-by: Xin He <xin3.he@intel.com>
Contributor
There was a problem hiding this comment.
Pull request overview
Adds initial support for WOQ (weight-only quantization) model inputs by extending the weight-type detection/conversion framework and adding a CPU test that exercises loading and converting a WOQ model to high precision.
Changes:
- Introduces
ModuleWeightType.WOQand registers a newWOQHandlerfor detection/conversion inauto_round/utils/weight_handler.py. - Adds a new CPU test (
test_w4a16) that loads a WOQ model and asserts WOQ detection + conversion behavior.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 4 comments.
| File | Description |
|---|---|
auto_round/utils/weight_handler.py |
Adds WOQ enum value and a new WOQHandler intended to detect/convert WOQ quantized layers. |
test/test_cpu/advanced/test_low_precision_input_model.py |
Adds a new test case for a WOQ (w4a16) model path and validates detection/conversion. |
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
for more information, see https://pre-commit.ci
Signed-off-by: Xin He <xin3.he@intel.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Signed-off-by: Sun, Xuehao <xuehao.sun@intel.com>
…h failure (#1621) Signed-off-by: Xin He <xin3.he@intel.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
…hemes in utils and tests (#1643) Signed-off-by: Xin He <xin3.he@intel.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Signed-off-by: Xin He <xin3.he@intel.com>
Signed-off-by: Xin He <xin3.he@intel.com>
… during module conversion Signed-off-by: Xin He <xin3.he@intel.com>
Contributor
Author
|
/azp run Unit-Test-CUDA-AutoRound |
|
Azure Pipelines successfully started running 1 pipeline(s). |
Contributor
Author
|
Will update to fix CI after this PR is merged. |
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
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.
Description
Please briefly describe your main changes, the motivation.
Type of Change
Related Issues
Fixes or relates to #
Checklist Before Submitting