Fastest, smallest, and fully autonomous AI assistant infrastructure written in Zig.
ZigMIT Licenseactive
9 projectsData & Science › Large Language Model
Fastest, smallest, and fully autonomous AI assistant infrastructure written in Zig.
ZigMIT Licenseactive
Native LLM inference server for Apple Silicon (MLX + GGUF) with OpenAI- and Anthropic-compatible APIs; ships MLX Core, a macOS menu-bar app. MIT.
ZigOtheractive
Inference LLaMA 2 in one file of pure Zig.
ZigMIT Licenseactive
Zig build for a terminal-based chat client for an assistant-style large language model with ~800k GPT-3.5-Turbo Generations based on LLaMA.
CGNU General Public License v3.0dormant
ZigFormer is a transformer-based LLM implemented in pure Zig.
ZigMIT Licensesteady
Inference LLaMA 2 in pure Zig.
ZigMIT Licenseslowingarchived
Neural Network Inference Engine in Zig. GPT2 inference engine written in Zig. The inference engine can run NanoGPT.
Zigdormant
Ollama Zig library.
ZigMIT Licenseslowing
Educational: build an LLM in Zig from scratch — tensors to text generation.
ZigMIT Licenseactive