onnxruntime
Skip redundant present_key/value copy when aliased to external KV cache (follow-up to #29715)
#31150

Open

Skip redundant present_key/value copy when aliased to external KV cache (follow-up to #29715) #31150

titaiwangms wants to merge 5 commits into main from copilot/cudnn-sdpa-decode-phase3

Add NOTE documenting Phase 2 (internal-cache cuDNN decode) investigat…

a830faed

Add NOTE documenting Phase 3 (cuDNN SDPA prefill chunking) investigat…

9b36e7dc

Skip redundant present_key/value D2D copy when aliased to KV cache

f7a45423

Address review findings for present_kv copy-skip fix

cb979984

titaiwangms requested a review from

copilot-pull-request-reviewer 4 days ago

copilot-pull-request-reviewer commented on 2026-07-30

titaiwangms marked this pull request as ready for review 4 days ago

titaiwangms requested a review from

tianleiwu 4 days ago

titaiwangms added ep:CUDA

tianleiwu commented on 2026-07-31

Address review findings on present_kv copy-skip PR (#31150)

f5ba8eac

titaiwangms requested a review from

tianleiwu 5 hours ago

Reviewers

tianleiwu

Assignees

No one assigned

Labels

ep:CUDA

Milestone

No milestone