cuda : improve text-generation and batched decoding performance #5983
build.yml
on: pull_request
Matrix: windows-latest-cmake-cublas
Matrix: windows-latest-cmake
ubuntu-focal-make
1m 37s
ubuntu-latest-cmake
2m 41s
macOS-latest-make
2m 58s
macOS-latest-cmake
2m 4s
macOS-latest-cmake-ios
1m 38s
macOS-latest-cmake-tvos
1m 52s
Matrix: macOS-latest-swift
Matrix: ubuntu-latest-cmake-mpi
Matrix: ubuntu-latest-cmake-sanitizer
release
0s