[Relax] Disable fusion for fetching from the packed params in FuseOps #17198
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
The order of bindings in the fusion result is determined by the first binding in each partition group. When the packed param tuple is used, the function usually begins with a numbers of `TupleGetItem` to unpack the param tuple. Previously `TupleGetItem` is treated as `kInjective`, this causes any operation that relies purely on these params to be moved to the beginning of the function and increases the memory usage of the intermediate results.
tqchen
approved these changes
Jul 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Outdated suggestions cannot be applied.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.
The order of bindings in the fusion result is determined by the first binding in each partition group. When the packed param tuple is used, the function usually begins with a numbers of
TupleGetItemto unpack the param tuple. PreviouslyTupleGetItemis treated askInjective, this causes any operation that relies purely on these params to be moved to the beginning of the function and increases the memory usage of the intermediate results.cc @tqchen