Skip to content
Test CUDA Windows Export

[ET-VK][ez] Make q8ta_conv2d use 4C1W layout #1906

Sign in to view logs

[ET-VK][ez] Make q8ta_conv2d use 4C1W layout

[ET-VK][ez] Make q8ta_conv2d use 4C1W layout #1906

Triggered via pull request February 13, 2026 03:57
@SS-JIASS-JIA
synchronize #17390
gh/SS-JIA/421/head
Status Success
Total duration 33m 28s
Artifacts 4

cuda-windows.yml

on: pull_request
Matrix: export-model-cuda-windows-artifact
Fit to window
Zoom out
Zoom in

Artifacts

Produced during runtime
Name Size Digest
mistralai-Voxtral-Mini-3B-2507-cuda-windows-non-quantized Expired
6.82 GB
sha256:4a43fd7eaf61cad7cf320a68a1b4c29bb91ae10a35a9166645b5ac7be5700028
mistralai-Voxtral-Mini-3B-2507-cuda-windows-quantized-int4-weight-only Expired
6.15 GB
sha256:fbabc26fe7a95bfb226d43974de30d07cdaf2639f9a9c9e487acefae0b5ff4e9
nvidia-parakeet-tdt-cuda-windows-non-quantized Expired
954 MB
sha256:d54a06b945a24ea356dcace33e39839ea9cea86b3da908989f85504725b3e648
nvidia-parakeet-tdt-cuda-windows-quantized-int4-weight-only Expired
432 MB
sha256:77eed059519beb47f6a55a9bcacf12d9804ec1ad97dd3aa49fecdbdabcfdc729