Models
Models that work with yzma, and the command for each one.
Guides
How to do specific tasks with yzma.
Chat templates
How to put your messages in the shape that a model expects.
Sampling
How to control which token the model takes next.
Multimodal input
Send images, audio, and video to a model.
Tool calling
How a model calls your Go functions.
Install from your program
Download the llama.cpp libraries with Go code.
Custom resolvers
Install the llama.cpp libraries from your own source.
Verify an installation
Check that the llama.cpp libraries are the files that the release published.
Build for a browser
Threads, headers, WebGPU, and the limits of a page.
Cross compiling
Build for another operating system or another processor.