Skip to content

WIP: [GPU] Use FP32 accumulator for QK multiplication for 2nd+ token calculation in PagedAttention #18555

WIP: [GPU] Use FP32 accumulator for QK multiplication for 2nd+ token calculation in PagedAttention

WIP: [GPU] Use FP32 accumulator for QK multiplication for 2nd+ token calculation in PagedAttention #18555

Triggered via pull request January 24, 2025 15:36
Status Success
Total duration 19m 24s
Artifacts 7

ubuntu_20.yml

on: pull_request
Debian Packages  /  Debian Packages
1m 42s
Debian Packages / Debian Packages
C++ unit tests  /  C++ unit tests
52s
C++ unit tests / C++ unit tests
Samples  /  Samples
Samples / Samples
Matrix: dGPU Tests
Waiting for pending jobs
Matrix: iGPU Tests
Waiting for pending jobs
ci/gha_overall_status_ubuntu_20
0s
ci/gha_overall_status_ubuntu_20
Fit to window
Zoom out
Zoom in

Annotations

2 warnings
Smart_CI
ubuntu-latest pipelines will use ubuntu-24.04 soon. For more details, see https://github.com/actions/runner-images/issues/10636
ci/gha_overall_status_ubuntu_20
ubuntu-latest pipelines will use ubuntu-24.04 soon. For more details, see https://github.com/actions/runner-images/issues/10636

Artifacts

Produced during runtime
Name Size
build_logs
2.59 KB
openvino_debian_packages
53.7 MB
openvino_developer_package
28 MB
openvino_package
54.2 MB
openvino_tests
190 MB
openvino_wheels
51.1 MB
test-results-cpp
3.4 KB