Skip to content

ggml-zdnn: fix #15414, activate FP16 and BF16 acceleration and incorr… #14

ggml-zdnn: fix #15414, activate FP16 and BF16 acceleration and incorr…

ggml-zdnn: fix #15414, activate FP16 and BF16 acceleration and incorr… #14

Triggered via push September 13, 2025 06:31
Status Failure
Total duration 56m 48s
Artifacts 12

release.yml

on: push
Matrix: ubuntu-22-cpu
Matrix: windows-cpu
Matrix: windows-cuda
Matrix: windows-hip
Matrix: windows
release
0s
release
Fit to window
Zoom out
Zoom in

Annotations

1 error and 11 warnings
macOS-x64
Process completed with exit code 2.
macOS-x64
Cache not found for keys: ccache-macOS-latest-cmake-x64-
windows (opencl-adreno, arm64, -G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-window...
Cache not found for keys: ccache-windows-latest-cmake-opencl-adreno-arm64-
windows-cpu (arm64)
Cache not found for keys: ccache-windows-latest-cmake-cpu-arm64-
windows-cpu (x64)
Cache not found for keys: ccache-windows-latest-cmake-cpu-x64-
ubuntu-22-cpu (x64, ubuntu-22.04)
Cache not found for keys: ccache-ubuntu-cpu-cmake-
windows (vulkan, x64, -DGGML_VULKAN=ON, ggml-vulkan)
Cache not found for keys: ccache-windows-latest-cmake-vulkan-x64-
macOS-arm64
Cache not found for keys: ccache-macOS-latest-cmake-arm64-
ubuntu-22-vulkan
Cache not found for keys: ccache-ubuntu-22-cmake-vulkan-
windows-sycl
Cache not found for keys: ccache-windows-latest-cmake-sycl-
windows-hip (radeon, gfx1100;gfx1101;gfx1102;gfx1030;gfx1031;gfx1032)
Cache not found for keys: ccache-windows-latest-cmake-hip-radeon-x64-
windows-cuda (12.4)
Cache not found for keys: ccache-windows-cuda-12.4-

Artifacts

Produced during runtime
Name Size Digest
cudart-llama-bin-win-cuda-12.4-x64.zip
372 MB
sha256:142a093b6db45916b196618c6505c4ff08268e4733a2e6b3b4e89a5ee83f3af1
llama-b6458-xcframework
84.3 MB
sha256:e9e6e5075c99b333229be92e08c7f19374e5416bfef8017ec3559c0f5e661c1e
llama-bin-macos-arm64.zip
11.2 MB
sha256:c120200e587b306d09acd309d30716aeff69d8deb76716a02f249b8731b3d538
llama-bin-ubuntu-vulkan-x64.zip
25.4 MB
sha256:d09a37b1006b5ca0fc90adf18a85b383734f220cfb5a58f92483e1b3f36f65aa
llama-bin-ubuntu-x64.zip
13.1 MB
sha256:d374fcf903697a8017939202dbe2097a7d8a152a6faca20a811180701b15075a
llama-bin-win-cpu-arm64.zip
11.3 MB
sha256:08d2b31d7d10f7e19371debac9f1a7a4bf0d4de78aecb1936b6d385a5bdfdb54
llama-bin-win-cpu-x64.zip
14.3 MB
sha256:6f86f1e92dec33ffa214381d43abfdcf9f1d22ccfac1216135c466e2de953bae
llama-bin-win-cuda-12.4-x64.zip
131 MB
sha256:dd2ac4f790ed73b6eac1e79cb20826bf1cbd958e7465e9ffed58a8c431bc7846
llama-bin-win-hip-radeon-x64.zip
264 MB
sha256:6d71296dba8da5735973e67e08f6dfb7793c2d7b1eca87dd68b4596c9dd30284
llama-bin-win-opencl-adreno-arm64.zip
110 KB
sha256:c40e0bba155e2d343e28b6bcca4b8e4a896b87effd033fb2a9c83ca56717dd4e
llama-bin-win-sycl-x64.zip
80 MB
sha256:23964bf019f85a34d88208bfaa8af7bbef1fb27933f56eaf66e620144a1679e2
llama-bin-win-vulkan-x64.zip
11.4 MB
sha256:333854890cbe8c7a6868334dc09b6b7314cd2c754652f1578fce89dc487226d8