reduce peak RAM usage during conversion#5
Open
spudone wants to merge 1 commit intoFastFlowLM:mainfrom
Open
Conversation
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
do not merge to main
This may be worth merging to its own branch. I don't have time to do an in-depth review though. I have done a successful run on a 32GB model file with these changes but I have not extensively tested model output / behavior.
The changes are designed to use zero-copy and chunked disk offload during conversion. Memory usage during conversion is about 1.2x model size, versus the original code requiring 2-2.5x.
The goal was to allow conversion of larger models without oom / crash.
If someone finds it useful, please pick it up and continue.