Paged attention #1460
Closed
Paged attention #1460
Conversation
This file contains 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
jiazhihao
added
the
inference
Bob-Chen222
force-pushed
the
paged_attention
branch
from
3e33eec
to
0493c12
Compare
Bob-Chen222
force-pushed
the
paged_attention
branch
from
0493c12
to
1297687
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Description of changes:
This PR adds page manager into the specscheduler branch.
Specifically, page manager is responsible for the allocation and deallocation of physical pages (GPU memory) that are used to store tokens' key value cache.
This version of page manager is many commits behind the newest version of main branch (i.e. specscheduler branch) and I will try to merge main branch into this branch in the next few days and do some further testing. It would be good if you can take a look and see if you have any questions on the current design and implementation.
This change is