certik/fastGPT
Fast GPT-2 inference written in Fortran
Fast GPT-2 inference written in Fortran
Learn how LLMs work by building one in Zig -- from tensors to text generation.
Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~1500 lines of vanilla Javascript.
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
PyTorch Implementation of OpenAI GPT-2
A high-performance Ethereum Virtual Machine implementation in Zig, featuring parallel transaction execution and comprehensive EVM opcode support.
1 capture since 2026-06-09