Efficient Training (including pre-training and fine-tuning) for Big Models

A high performance N-dimensional array library for Rust

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

Provide structs and methods to operate riscv aclint device.

这是一个简单的技术科普教程项目，主要聚焦于解释一些有趣的，前沿的技术概念和原理。每篇文章都力求在 5 分钟内阅读完成。

handle gguf files

开源软件通识课程 (Introduction to Open Source Software)，本课程暂定设计面向信息大类专业的大一学生

RustSBI Specialized Domain Knowledge Quiz LLM

实验：rust 实现 llama2 推理

An experimental modular OS written in Rust.

没分支的 rCore-Tutorial

A lightweight WebAssembly runtime that is fast, secure, and standards-compliant

Embedded Rust peripheral driver for Bouffalo IoT chips

A super-simple compiler demoing how to talk to LLVM from Rust

🥥 Coco AI App - Search, Connect, Collaborate, Your Personal AI Search and Assistant, all in one space.

A language and compiler for irregular tensor programs.

GPU scientific computing on every platform

加速100～3000倍的github.com

A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

沐曦加速器驱动（rust binding）

摩尔线程显卡驱动（rust binding）

Distributed LLM and StableDiffusion inference for mobile, desktop and server.

CUDA Matrix Multiplication Optimization

The easiest & fastest way to run customized and fine-tuned LLMs locally or on the edge

An implementation of a LRU cache