-
Notifications
You must be signed in to change notification settings - Fork 2.7k
[NPUW]Implement prefix caching. #31669
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open
intelgaoxiong
wants to merge
35
commits into
openvinotoolkit:master
Choose a base branch
from
intelgaoxiong:xiong/prefix_caching
base: master
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
[NPUW]Implement prefix caching. #31669
intelgaoxiong
wants to merge
35
commits into
openvinotoolkit:master
from
intelgaoxiong:xiong/prefix_caching
+1,328
−155
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
a7a59db
to
48f060e
Compare
build_jenkins |
719eac4
to
c9ee5f6
Compare
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Signed-off-by: intelgaoxiong <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Labels
category: build
OpenVINO cmake script / infra
category: NPU
OpenVINO NPU plugin
category: NPUW
NPUW plugin
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:
This PR implements prefix caching in NPUW.
In existing inference engines, the KV cache of a request is discarded after processing is completed, preventing the KV cache from being reused across multiple calls and significantly slowing down the execution.
https://arxiv.org/pdf/ 2312.07104 proposed a new technique to reuse KV cache automatically across multiple generation calls.
Tickets: