AIFoundation 主要是指AI系统遇到大模型，从底层到上层如何系统级地支持大模型训练和推理，全栈的核心技术。

code reading for tvm

examples for tvm schedule API

This is the top-level repository for the Accel-Sim framework.

A bunch of coding tutorials for my Youtube videos on Neural Network Quantization.

Course materials for MIT6.5940: TinyML and Efficient Deep Learning Computing

《Effective Modern C++》- 完成翻译

Achieve a tiny STL in C++11

Fast SpMM implementation on GPUs for GNN (IPDPS'23)

study of Ampere' Sparse Matmul

21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

Code for ACM MobiCom 2024 paper "FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices"

PyTorch tutorials.

健康学习到150岁 - 人体系统调优不完全指南

中文的C++ Template的教学指南。与知名书籍C++ Templates不同，该系列教程将C++ Templates作为一门图灵完备的语言来讲授，以求帮助读者对Meta-Programming融会贯通。(正在施工中)

A small C compiler

heterogeneity-aware-lowering-and-optimization

Solve puzzles. Learn CUDA.

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.

Inference Llama 2 in one file of pure C

Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

Advanced Scalable Systems for X

This repository contains tutorials and examples for Triton Inference Server

Tile primitives for speedy kernels

My learning notes/codes for ML SYS.

Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training

PKU OS course project and notes based on Nachos and XV6