[feat] KvCompOnDevice: per-KV-head Top-K for Qwen#588
Merged
mag1c-h merged 1 commit intoModelEngine-Group:0.2.0-releasefrom Dec 26, 2025
Merged
[feat] KvCompOnDevice: per-KV-head Top-K for Qwen#588mag1c-h merged 1 commit intoModelEngine-Group:0.2.0-releasefrom
mag1c-h merged 1 commit intoModelEngine-Group:0.2.0-releasefrom
Conversation
wangwenxin0312
requested review from
hek14,
leideng,
mag1c-h,
pengwwang,
wuhuxiao and
ygwpz
as code owners
wangwenxin0312
force-pushed
the
dev_kvcomp_qwen
branch
from
0c5287b to
3d417e3
Compare
wuhuxiao
approved these changes
Dec 25, 2025
mag1c-h
approved these changes
Dec 26, 2025
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Purpose
What this PR does / why we need it?
Enable per-KV-head Top-K selection to support Qwen models with multiple KV heads (GQA) in KvCompOnDevice.
Modifications
Does this PR introduce any user-facing change?
Ensure the Hamming distance kernel correctly outputs scores for each KV head.
Update the Top-K selection logic to handle multi-KV-head outputs from the Hamming distance operator
Test
How was this patch tested?
python examples/offline_inference_kvcomphbm.py