COPY OF 2532#2555
Closed
xiaoyu-work wants to merge 1 commit into
Closed
Conversation
Fix the ONNX calibration path: Quark 0.12 rejects extra inputs in the calibration data reader, so pass model_path/io_config to filter out dataset labels (e.g. `class`) that are not model inputs. Update the Torch path for the Quark 0.12 API: replace the removed `revert_model_patching` and the deprecated `prepare_for_moe_quant` (which now raises on transformers>=5) with `preprocess_for_quantization`. Bump the required amd-quark version to >=0.12.0.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fix the ONNX calibration path: Quark 0.12 rejects extra inputs in the calibration data reader, so pass model_path/io_config to filter out dataset labels (e.g.
class) that are not model inputs.Update the Torch path for the Quark 0.12 API: replace the removed
revert_model_patchingand the deprecatedprepare_for_moe_quant(which now raises on transformers>=5) withpreprocess_for_quantization.Bump the required amd-quark version to >=0.12.0.
Describe your changes
Checklist before requesting a review
lintrunner -a(Optional) Issue link