Skip to content

[CUDA] Support FP8 (E4M3) KV Cache for Group Query Attention #3737

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

[CUDA] Support FP8 (E4M3) KV Cache for Group Query Attention #3737

Triggered via pull request February 14, 2026 04:12
Status Success
Total duration 36m 26s
Artifacts 4

react_native.yml

on: pull_request
Build Android AAR Packages
22m 10s
Build Android AAR Packages
React Native CI iOS Build
18m 18s
React Native CI iOS Build
React Native CI Android
10m 41s
React Native CI Android
React Native CI iOS E2E Tests
15m 7s
React Native CI iOS E2E Tests
Fit to window
Zoom out
Zoom in

Annotations

3 warnings
React Native CI iOS Build
Terrapin tool path provided but not found at 'C:/local/Terrapin/TerrapinRetrievalTool.exe'. Attempting direct download for vcpkg.
Build Android AAR Packages
Terrapin tool path provided but not found at 'C:/local/Terrapin/TerrapinRetrievalTool.exe'. Attempting direct download for vcpkg.
React Native CI iOS E2E Tests
Terrapin tool path provided but not found at 'C:/local/Terrapin/TerrapinRetrievalTool.exe'. Attempting direct download for vcpkg.

Artifacts

Produced during runtime
Name Size Digest
android-test-results
35.7 KB
sha256:bc8c4b8008080395e432e1f2b9f924c7ff1e41118ed11ef24bbd4764579a904d
ios-test-results
55.7 KB
sha256:64b73091ff433ee9af6f74d12f8fff1395d364a6605080c6b4cb6bf5c219c1af
ios_pod
9.8 MB
sha256:09a5cf1b95f04d0d698d79f5d35a39c5f71c75099d9466960ad1ca1f53b7170c
onnxruntime-android-full-aar
7.73 MB
sha256:9a6f1593904e6978901c2b275e1af9d6fd74da6a36fa3c63b049bf2ca7329ff8