onnxruntime
Add quantized KV cache support in CPU GroupQueryAttention
#28576

Merged

Add quantized KV cache support in CPU GroupQueryAttention #28576

kunal-vaishnavi merged 5 commits into main from tlwu/20260519/gqa_cpu_quantized_kv_cache

Add quantized kv cache support in GQA cpu

8c99df18

fix build

475506c4

tianleiwu requested a review from

copilot-pull-request-reviewer 87 days ago

tianleiwu requested a review from

apsonawane 87 days ago

copilot-pull-request-reviewer commented on 2026-05-19

tianleiwu requested a review from

kunal-vaishnavi 87 days ago

Address Copilot review feedback

9c225ef5

tianleiwu force pushed from e9d0bbcd to 9c225ef5 87 days ago

remove unused code

2ad76d7a

kunal-vaishnavi commented on 2026-05-20

kunal-vaishnavi dismissed these changes on 2026-05-20

apsonawane dismissed these changes on 2026-05-20

Fix CI: INT4 test verifier unpack bug, update OperatorKernels.md

10e054a7

tianleiwu dismissed their stale review via 10e054a7 87 days ago

tianleiwu requested a review from

kunal-vaishnavi 87 days ago

tianleiwu requested a review from

apsonawane 87 days ago

kunal-vaishnavi approved these changes on 2026-05-20

kunal-vaishnavi enabled auto-merge (squash) 87 days ago

kunal-vaishnavi merged 6fbda6d8 into main 87 days ago

kunal-vaishnavi deleted the tlwu/20260519/gqa_cpu_quantized_kv_cache branch 87 days ago

Reviewers

kunal-vaishnavi

apsonawane

Assignees

No one assigned

Labels

None yet

Milestone

No milestone