[Fix][Dlight] Fix GeneralReduction for log-sum-exp #16923
Merged
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
c8280e5 to
7907a27
Compare
This PR fixes the GeneralReduction dlight rule so that it can support scheduling log-sum-exp function. Prior to this issue, the rule makes a strong assumption on the pattern of the given function, which allows scheduling softmax, but fails to schedule log-sum-exp due to pattern mismatch. This PR enhances the rule and makes it able to match the pattern of log-sum-exp and apply subsequent scheduling. A regression test is added.
7907a27 to
1580ab5
Compare
tqchen
approved these changes
Apr 26, 2024
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Outdated suggestions cannot be applied.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.
This PR fixes the GeneralReduction dlight rule so that it can support scheduling log-sum-exp function.
Prior to this issue, the rule makes a strong assumption on the pattern of the given function, which allows scheduling softmax, but fails to schedule log-sum-exp due to pattern mismatch. This PR enhances the rule and makes it able to match the pattern of log-sum-exp and apply subsequent scheduling.
A regression test is added.