[KVCache] Add KV Cache for CPU Runtime - #17615
Merged
Merged
Conversation
mengshyu
force-pushed
the
0129-kvcache-cpu
branch
4 times, most recently
from
January 29, 2025 20:00
8e516a2 to
69b54e7
Compare
This PR introduces KV Cache support for the CPU runtime: * Implementation of KV Cache TIR for CPU-based processing. * Updates to the relevant runtime components to integrate KV Cache. Co-authored-by: HMZ <mzhuang@pllab.cs.nthu.edu.tw> Co-authored-by: ShouChenChiu <scchiu@pllab.cs.nthu.edu.tw>
mengshyu
force-pushed
the
0129-kvcache-cpu
branch
from
January 30, 2025 17:21
69b54e7 to
68055c7
Compare
mengshyu
changed the title
Contributor
Author
|
Hi @MasterJH5574 , could you help to review this PR? Thanks. cc. @tqchen |
Contributor
|
Thank you @mengshyu! I wonder if we can add some unit tests? We can have a file that is similar to https://github.com/apache/tvm/blob/main/tests/python/relax/test_runtime_builtin_paged_attention_kv_cache_tir.py which focuses on the CPU backend. |
mengshyu
force-pushed
the
0129-kvcache-cpu
branch
from
February 2, 2025 16:12
4e2fb21 to
bef3b4c
Compare
MasterJH5574
approved these changes
Feb 2, 2025
MasterJH5574
left a comment
MasterJH5574
left a comment
Contributor
There was a problem hiding this comment.
LGTM, thank you @mengshyu!
ShiboXing
pushed a commit
to ShiboXing/tvm
that referenced
this pull request
Aug 10, 2025
* [KVCache] Add KV Cache for CPU Runtime This PR introduces KV Cache support for the CPU runtime: * Implementation of KV Cache TIR for CPU-based processing. * Updates to the relevant runtime components to integrate KV Cache. Co-authored-by: HMZ <mzhuang@pllab.cs.nthu.edu.tw> Co-authored-by: ShouChenChiu <scchiu@pllab.cs.nthu.edu.tw> * Add unit test --------- Co-authored-by: HMZ <mzhuang@pllab.cs.nthu.edu.tw> Co-authored-by: ShouChenChiu <scchiu@pllab.cs.nthu.edu.tw>
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.
This PR introduces KV Cache support for the CPU runtime: