[NPUW]Fixed high memory footprint with blob cache.#36195
Merged
dmatveev merged 1 commit intoJun 3, 2026
Merged
Conversation
intelgaoxiong
changed the title
github-actions
Bot
added
category: NPU
dmatveev
approved these changes
Jun 2, 2026
Signed-off-by: intelgaoxiong <xiong.gao@intel.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Details:
Very high memory footprint when running LLM with blob cache (import blob) - 20GB RSS
But it was only 8GB when running LLM with the default compilation approach.
Root cause is we exported / imported for every repeating layer.
RSS increased after importing for each repeating layer and then the accumulated RSS is very huge.
Tickets:
AI Assistance: