Skip to content
Documentation

[CPU] Matmul node support quantized outputs for f16 bias to avoid unnecessary reorder following #136543

Sign in to view logs

[CPU] Matmul node support quantized outputs for f16 bias to avoid unnecessary reorder following

[CPU] Matmul node support quantized outputs for f16 bias to avoid unnecessary reorder following #136543

Triggered via pull request November 15, 2024 02:42
@liubo-intelliubo-intel
synchronize #27557
liubo-intel:liubo/fix_fullyconnected_quantized_output_issue
Status Success
Total duration 4m 27s
Artifacts 2

build_doc.yml

on: pull_request
Build_Doc
4m 16s
Build_Doc
Fit to window
Zoom out
Zoom in

Artifacts

Produced during runtime
Name Size
openvino_docs_html_27557.zip
43.1 MB
sphinx_build_log_27557.log
1.2 KB