Skip to content

[CB] Split token streaming and generation to different threads for all CB based pipelines #5762

[CB] Split token streaming and generation to different threads for all CB based pipelines

[CB] Split token streaming and generation to different threads for all CB based pipelines #5762

Triggered via pull request January 17, 2025 15:25
Status Failure
Total duration 1h 14m 9s
Artifacts 4

linux.yml

on: pull_request
Download OpenVINO
1m 9s
Download OpenVINO
Matrix: genai_build_cmake
Matrix: genai_build_samples
Matrix: genai_tests_wheel
Matrix: genai_samples_tests
ci/gha_overall_status_linux
0s
ci/gha_overall_status_linux
Fit to window
Zoom out
Zoom in

Annotations

3 errors and 1 warning
Python (LLM & VLM) Tests (wheel)
The job running on runner aks-4-cores-16gb-runner-6d8f2-9b728 has exceeded the maximum execution time of 60 minutes.
Python (LLM & VLM) Tests (wheel)
The operation was canceled.
ci/gha_overall_status_linux
Process completed with exit code 1.
ci/gha_overall_status_linux
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
genai_archive_Release
17.4 MB
genai_samples_Release
2.03 MB
genai_wheels
16.8 MB
ubuntu22
140 MB