onnxruntime
[CUDA] Support FP8 (E4M3) KV Cache for Group Query Attention
#27321

Merged

[CUDA] Support FP8 (E4M3) KV Cache for Group Query Attention #27321

tianleiwu merged 12 commits into main from tlwu/20260211/gqa_fp8_kv_cache

fix build errors

9aa8deb7

Support fp8 kv cache

019a2b15

update comments

abcbdadc

tianleiwu marked this pull request as draft 122 days ago

tianleiwu requested a review from

copilot-pull-request-reviewer 122 days ago

update doc

3a260ef8

copilot-pull-request-reviewer commented on 2026-02-12

udpate io binding helper type mapping

9ad73e43

copilot feedback

e83141ab

update test

d28d92da

tianleiwu marked this pull request as ready for review 122 days ago

github-actions commented on 2026-02-12

lintrunner

2a52fc15

tianleiwu commented on 2026-02-12

consolidate cuda type

068d0529

tianleiwu requested a review from

kunal-vaishnavi 121 days ago

Merge remote-tracking branch 'origin/main' into tlwu/20260211/gqa_fp8…

b073388c

tianleiwu requested a review from

titaiwangms 121 days ago

refine

3d507bd0

fix build

2a257802

kunal-vaishnavi commented on 2026-02-16

tianleiwu requested a review from

kunal-vaishnavi 117 days ago

kunal-vaishnavi approved these changes on 2026-02-17

titaiwangms commented on 2026-02-17

tianleiwu enabled auto-merge (squash) 116 days ago

tianleiwu merged 19c9efc4 into main 116 days ago

tianleiwu deleted the tlwu/20260211/gqa_fp8_kv_cache branch 116 days ago

Reviewers

kunal-vaishnavi

titaiwangms

github-actions

copilot-pull-request-reviewer

Assignees

No one assigned

Labels

None yet

Milestone

No milestone

onnxruntime [CUDA] Support FP8 (E4M3) KV Cache for Group Query Attention #27321 Merged

[CUDA] Support FP8 (E4M3) KV Cache for Group Query Attention #27321

onnxruntime
[CUDA] Support FP8 (E4M3) KV Cache for Group Query Attention
#27321

Merged