[Unity][Dlight] GeMV rule skip cases of "outer dim being grouped" #284
Conversation
This file contains 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
Prior to this PR, the GeMV contains an assumption that "the grouped dimension of the largest tensor in GeMV must has the same iter type as the innermost dimension", which is enforced by an assertion. Since AutoGPTQ quantization only supports KN GeMV layout, the decode-GeMV generated under the AutoGPTQ quantization has the pattern where the reduction dimension is not the innermost and is grouped. This pattern does not follow the assersion above and thus an assertion error will be thrown. This PR updates the logic to skip transforming such cases, instead of asserting the assumption. One real AutoGPTQ decode-GeMV workload is added as a test case for future awareness.
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Outdated suggestions cannot be applied.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.
Prior to this PR, the GeMV contains an assumption that "the grouped dimension of the largest tensor in GeMV must has the same iter type as the innermost dimension", which is enforced by an assertion.
Since AutoGPTQ quantization only supports KN GeMV layout, the decode-GeMV generated under the AutoGPTQ quantization has the pattern where the reduction dimension is not the innermost and is grouped. This pattern does not follow the assersion above and thus an assertion error will be thrown.
This PR updates the logic to skip transforming such cases, instead of asserting the assumption. One real AutoGPTQ decode-GeMV workload is added as a test case for future awareness.