GitHub Trending repo Repositories Jul 5 2 views

matteo-grella/fucina: CPU-first tensor/autograd runtime and LLM inference engine in pure Zig — eager execution, GGUF in and out, LoRA training on CPU, benchmarked pairwise against llama.cpp.

by matteo-grella

CPU-first tensor/autograd runtime and LLM inference engine in pure Zig — eager execution, GGUF in and out, LoRA training on CPU, benchmarked pairwise against llama.cpp.

Read Original
Fine-Tuning LLM

Metadata

Stars
6
Language
Zig
Watchers
6
License
MIT

Related