compile one observed function for all CopyParamsByTemplate fallback batches#4692
Merged
Merged
Conversation
… batches `CopyParamsByTemplate` compiled a separate observed function for each non-contiguous batch of symbolic-fallback parameters. Each compile pays `build_function_wrapper`'s large fixed per-call cost, so N batches cost N times that overhead. Compile a single observed function over all fallback symbols instead, and have `FallbackSlice` template entries index into its result.
AayushSabharwal
approved these changes
Jul 1, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
CopyParamsByTemplatecompiled a separate observed function for eachnon-contiguous batch of symbolic-fallback parameters. Each compile pays
build_function_wrapper's large fixed per-call cost, so N batches cost Ntimes that overhead. Compile a single observed function over all fallback
symbols instead, and have
FallbackSlicetemplate entries index into itsresult.
This takes a fairly large model from
to