quant ops: Dequantize weight in-place (reduce flux2 VRAM usage) #10935
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
In flux2 these weights are huge (200MB). As plain_tensor is a throw-away deep copy, do this multiplication in-place to save VRAM.
1 task
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Outdated suggestions cannot be applied.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.
In flux2 these weights are huge (200MB). As plain_tensor is a throw-away deep copy, do this multiplication in-place to save VRAM.
This will at least improve (if not fully fix): #10891
Example test conditions:
RTX5090
--reserve-vram 8.9 (to emulate 3090 VRAM ceiling)
Before (peak is 23.3GB):
After (peak is 23.0GB):