hybridgroup/yzma

Go with your own intelligence - Write Go applications that directly integrate llama.cpp for local inference using hardware acceleration on Linux, macOS, Windows, & WebAssembly.

2 best points · 0 comments · 5 Hacker News posts · 670 GitHub stars · View on GitHub

Hacker News discussions

• Yzma – local Vision Language Models/LLMs in Go using llama.cpp without CGo (2 points, 0 comments, by deadprogram, 2025-10-08)
• Go apps can directly integrate llama.cpp for HW accelerated local inference (2 points, 0 comments, by deadprogram, 2025-12-02)
• Yzma = embedding+inference on VLM/LLM/SLM/TLM in pure Go using llama.cpp (1 points, 0 comments, by deadprogram, 2025-10-14)
• Pure Go hardware accelerated local inference on VLMs using llama.cpp (1 points, 0 comments, by deadprogram, 2025-11-07)
• Yzma 1.0 is out Go programs that run local models with hardware acceleration (1 points, 0 comments, by deadprogram, 2025-12-04)