[Feature] Cache Blend #467
Open
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
wuhuxiao
requested review from
HaoLi980405,
Zbm1996,
harrisonyhq,
hek14,
mag1c-h,
qyh111,
saki-daisuki,
summer-ai007,
wangwenxin0312,
xwLearnsLLM,
ygwpz,
yxkyong and
zbb200819
as code owners
wuhuxiao
force-pushed
the
dev-cache-blend-whx
branch
from
3931b2d to
0919b19
Compare
ygwpz
reviewed
Dec 4, 2025
| request_meta: dict[str, BlendRequestDispatchMeta] = field(default_factory=dict) | ||
|
|
||
|
|
||
| class UCMBlendConnector(UCMDirectConnector): |
Contributor
There was a problem hiding this comment.
it seem's no need to inherit from UCMDirectConnector but from KVConnectorBase_V1
Author
There was a problem hiding this comment.
the kv blocks load and dump are now implemented in UCMDirectConnector 's store. If there are contiguous kvcache load and dump api in kv store, we will inherit from KVConnectorBase_V1 and build specified kvcache dump, lookup, load functions
wuhuxiao
requested review from
FangRun2,
Tarrei and
flesher0813
as code owners
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Outdated suggestions cannot be applied.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.
Purpose
Context Independent Cache (Chunk Cache) is all you need
What this PR does / why we need it?
Modifications
Does this PR introduce any user-facing change?
Test
ENABLE_SPARSE=True
DATA_DIR=/home/data/kv_cache
MODEL_PATH=/home/models/mistralai/Mistral-7B-Instruct-v0.2
BLEND_DATASET_PATH=/home/datasets/LongBench/data/2wikimqa.jsonl
How was this patch tested?