CUDA: faster dequantize kernels for Q4_0 and Q4_1 (#4938) #108
build.yml
on: push
Matrix: windows-latest-cmake-cublas
Matrix: windows-latest-cmake
ubuntu-focal-make
1m 35s
ubuntu-latest-cmake
1m 43s
macOS-latest-make
4m 28s
macOS-latest-cmake
3m 39s
macOS-latest-cmake-ios
1m 11s
macOS-latest-cmake-tvos
1m 12s
ios-xcode-build
1m 21s
Matrix: macOS-latest-swift
Matrix: ubuntu-latest-cmake-mpi
Matrix: ubuntu-latest-cmake-sanitizer
release
46s
Annotations
1 error and 1 warning
windows-latest-cmake (avx512, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUIL...
Process completed with exit code 1.
|
release
The following actions uses node12 which is deprecated and will be forced to run on node16: actions/github-script@v3. For more info: https://github.blog/changelog/2023-06-13-github-actions-all-actions-will-run-on-node16-instead-of-node12-by-default/
|
Artifacts
Produced during runtime
Name | Size | |
---|---|---|
artifact
Expired
|
751 MB |
|