Release 5.0.3: OpenAI-compatible server, multimodal, and llama.cpp b9842 #496
publish.yml
on: pull_request
Start gate (abort window)
54s
Test (vmlens interleavings)
Cross-Compile manylinux_2_28 x86_64 (CUDA)
Cross-Compile Android aarch64 (OpenCL/Adreno)
Build and Test Windows 2025 x86_64 (Ninja Multi-Config + sccache, default)
Build and Test Windows 2025 x86_64 (MSVC / VS 2026, classifier)
Build and Test Linux aarch64
Cross-Compile Android aarch64
Build and Test Windows 2025 x86 (MSVC / VS 2026, classifier)
Build and Test Windows 2025 x86 (Ninja Multi-Config + sccache, default)
Build Windows 2025 x86_64 CUDA (Ninja + sccache)
Build Windows 2025 x86_64 Vulkan (Ninja + sccache)
Build Windows 2025 x86_64 OpenCL (Ninja + sccache)
Java Tests Windows 2025 x86_64 (default / Ninja)
0s
Java Tests Windows 2025 x86_64 (MSVC classifier)
0s
Attach Signed Binaries to GitHub Release
Update Snapshot Pre-release on GitHub
0s
Annotations
1 error
|
Publish
The run was canceled by @bernardladenthin.
|