[Unity] Paged KV Cache as LM Support#15910
Merged
tqchen merged 1 commit intoOct 15, 2023
Merged
Conversation
tqchen
reviewed
Oct 11, 2023
Contributor
Author
|
Mark as draft for an update of docstring and APIs. Sorry that it is not mature enough. |
MasterJH5574
force-pushed
the
unity-dev/2023-10-10-paged-kv-cache
branch
from
7671ddb to
4a5b263
Compare
Contributor
Author
|
Documented the paged KV cache and updated some of the interfaces. It's ready for review now. |
MasterJH5574
force-pushed
the
unity-dev/2023-10-10-paged-kv-cache
branch
from
4a5b263 to
36da7a4
Compare
tqchen
reviewed
Oct 12, 2023
tqchen
reviewed
Oct 12, 2023
tqchen
reviewed
Oct 12, 2023
tqchen
reviewed
Oct 12, 2023
tqchen
reviewed
Oct 12, 2023
tqchen
reviewed
Oct 12, 2023
tqchen
reviewed
Oct 12, 2023
MasterJH5574
force-pushed
the
unity-dev/2023-10-10-paged-kv-cache
branch
from
36da7a4 to
8ef57ba
Compare
tqchen
approved these changes
Oct 12, 2023
yongwww
reviewed
Oct 12, 2023
MasterJH5574
force-pushed
the
unity-dev/2023-10-10-paged-kv-cache
branch
2 times, most recently
from
4c80ff8 to
8ce79b9
Compare
This PR introduces the PagedKVCache object to Relax runtime for the KV cache value management in batching settings. One test file is included. Note that this file does not contain the test of attention function/kernel. That part will be uploaded and tested separately.
MasterJH5574
force-pushed
the
unity-dev/2023-10-10-paged-kv-cache
branch
from
8ce79b9 to
6a5c618
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 PR introduces the PagedKVCache object to
lm_support.ccfor the KV cache value management in batching settings.One test file is included. Note that this file does not contain the test of attention function/kernel. That part will be uploaded and tested separately.