Skip installing large aliased constant-folded weights - #4531
Open
micwill755 wants to merge 1 commit into
Open
Conversation
Avoid cpu().contiguous() copies of folded tensors that already share storage with module weights under offload_module_to_cpu, while still installing materialized folds.
3 tasks
github-actions
Bot
added
component: lowering
This was referenced Aug 19, 2026
Collaborator
|
Can you explain more about what is happening here? What situation are we avoiding by skipping constant folding? |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
cpu().contiguous()copies underoffload_module_to_cpu.PR 2 of 3 in a compile-startup stack; based on #4530.
Test plan
offload_module_to_cpu=True