用纯粹、无依赖的C语言训练和推理GPT的最原子化方法

microgpt 开源项目推荐(37 个)
microgpt 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 37 个仓库GPT in a QR Code ; The actual most atomic way to train and inference a GPT in pure, dependency-free JS/Python.
Interactive visualization of a minimal GPT implementation with autograd engine.
A complete GPT built from scratch in TypeScript with zero dependencies
The essence of text diffusion in ~150 lines of pure Python. Inspired by Karpathy's MicroGPT.
"Everything else is just for efficiency." — Karpathy's microgpt benchmarked across scalar autograd, NumPy, and PyTorch (RTX 5080)
like Karpathy, but micro: a live autopsy on your innoncent prompts
microgpt.cpp in 300 lines!
Minimal char-level GPT inspired by @karpathy's microGPT: multi-dataset runner for names, Pokémon, Shakespeare, Paul Graham essays and more. Educational, hackable, no fluff.
该项目在 GitHub 上没有填写描述
A small secret CTF for DevFest Pisa 2026: microgpt llm runs on python (pyodide) on a shell (vfs+common unix commands) on js
🦀 A complete GPT implemented from scratch in pure, dependency-free Rust. ~600 lines of educational code covering autograd, multi-head self-attention, RMSNorm, Adam optimization, and full training + inference. Built to understand how LLMs work from first principles.
A 1:1 Go port of Andrej Karpathy's microgpt. Pure Go, single file, no external dependencies.
A Swift port of Karpathy’s microgpt. Runs natively on Apple Silicon GPUs via Metal Performance Shaders Graph.
gpt inference optimization game
Rust port of @karpathy's microgpt.py. The most atomic way to train and run inference for a GPT, now in pure Rust with zero ML framework dependencies.
MiniGPT-16MB: The Ultra-Light Storyteller, driven by a high-performance Language Model (LLM) designed to run entirely in the browser. At under 16MB, this model is optimized for low-end hardware, mobile devices, and offline use.
Composable tiny intelligence from microgpt. Pure Python. Zero dependencies.
A compact Transformer model for character-level generation with Mixture-of-Experts, Rotary Attention, and F-gram contextual augmentation.
microGPT
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/microgpt。
- 该话题在 GitHub 上共有 37 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 1234 Star,覆盖 10 种主要语言,数据更新于 2026-11-07。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。