Linux (Ubuntu 24.04, Python 3.12)

NPUW: LLMInferRequest - not copy kvcache for last generated token #17595

Sign in to view logs

Triggered via pull request January 16, 2025 13:38

synchronize #28489

TolyaTalamanov:at/npuw-llm-pipeline-stop-when-kvcache-is-full

Status Success

Total duration 53m 13s

Artifacts 14

ubuntu_24.yml

on: pull_request

OpenVINO tokenizers extension / OpenVINO tokenizers extension

Debian Packages / Debian Packages

Samples / Samples

Python unit tests / Python unit tests

Pytorch Layer Tests / PyTorch Layer Tests

C++ unit tests / C++ unit tests

Python API tests / Python API tests

JAX Layer Tests / JAX Layer Tests

TensorFlow Layer Tests / TensorFlow Layer Tests

ci/gha_overall_status_ubuntu_24

Annotations

2 warnings

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_24

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	2.51 KB
openvino_debian_packages	55.9 MB
openvino_developer_package	28.8 MB
openvino_js_package	80.5 MB
openvino_package	56.4 MB
openvino_tests	200 MB
openvino_tokenizers_wheel	14 MB
openvino_wheels	53.3 MB
test-results-cpp	1.25 MB
test-results-python	34.9 KB
test-results-python-api-3.12	78.5 KB
test-results-python-jax-layers	16.8 KB
test-results-python-pytorch-layers	224 KB
test-results-python-tf-layers	94.4 KB