Reading the repo
Reading the repo
Assembly instructions
A hierarchical inference engine for frontier MoE models: hot experts on the GPU (CUDA, Vulkan), warm ones in RAM, cold ones streamed from NVMe. Written in C, runs on the hardware you already own.
Saved setup from 3 h ago
The maintainers included start-here.sh. Run it from the cloned folder after reading it.
bash start-here.sh
Also: START-HERE.bat
Will it work on my device?
curl -LO "https://github.com/JustVugg/colibri/releases/download/v2.1.0/colibri-v2.1.0-macos-arm64.tar.gz" tar -xzf "colibri-v2.1.0-macos-arm64.tar.gz"
No reports for macOS yet.
Opens a chat with this manual already filled in, for macOS. It uses your own account; gitmanual sends nothing.