[CPU] Cache FullyConnected weigths in scope of compile model#34492
Open
EgorDuplensky wants to merge 3 commits intoopenvinotoolkit:masterfrom
Open
[CPU] Cache FullyConnected weigths in scope of compile model#34492EgorDuplensky wants to merge 3 commits intoopenvinotoolkit:masterfrom
EgorDuplensky wants to merge 3 commits intoopenvinotoolkit:masterfrom
Conversation
This moves into out of the first inference and significanlty improves first token latency on LLMs Also it reduces peak memory usage alot, since most of the weights where transposed in scope of compile_model call anyway
Contributor
Author
|
@maxnick Could you please take a look |
maxnick
approved these changes
Mar 4, 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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This moves it out of the first inference and significantly improves
first token latency on LLMs
Also, it reduces peak memory usage a lot, since most of the weights
where transposed in scope of compile_model call anyway
The current state of test infrastructure does not allow to have a test for this logic
Details:
Tickets:
AI Assistance: