Skip to content
Back to pull request #4309

llama : per-layer KV cache #6741

Sign in to view logs

llama : per-layer KV cache

llama : per-layer KV cache #6741

Triggered via pull request December 7, 2023 10:35
@ggerganovggerganov
synchronize #4309
gg/per-layer-kv
Status Success
Total duration 18m 56s
Artifacts –

build.yml

on: pull_request
Matrix: windows-latest-cmake-cublas
Matrix: windows-latest-cmake
ubuntu-focal-make
1m 28s
ubuntu-focal-make
ubuntu-latest-cmake
1m 24s
ubuntu-latest-cmake
macOS-latest-make
1m 41s
macOS-latest-make
macOS-latest-cmake
3m 38s
macOS-latest-cmake
macOS-latest-cmake-ios
1m 53s
macOS-latest-cmake-ios
macOS-latest-cmake-tvos
1m 15s
macOS-latest-cmake-tvos
ios-xcode-build
1m 1s
ios-xcode-build
Matrix: macOS-latest-swift
Matrix: ubuntu-latest-cmake-mpi
Matrix: ubuntu-latest-cmake-sanitizer
release
0s
release
Fit to window
Zoom out
Zoom in

Annotations

1 error
windows-latest-cmake (avx512, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUIL...
Process completed with exit code 1.