Use Q4_K for attn_v for Q2_K_S when n_gqa >= 4 #7672
build.yml
on: pull_request
Matrix: windows-latest-cmake-cublas
Matrix: windows-latest-cmake
ubuntu-focal-make
1m 36s
ubuntu-latest-cmake
1m 41s
macOS-latest-make
2m 27s
macOS-latest-cmake
5m 8s
macOS-latest-cmake-ios
6m 35s
macOS-latest-cmake-tvos
1m 24s
ios-xcode-build
1m 51s
android-build
5m 23s
Matrix: macOS-latest-swift
Matrix: ubuntu-latest-cmake-mpi
Matrix: ubuntu-latest-cmake-sanitizer
release
0s
Annotations
10 errors and 4 warnings