some attention implements

Record and Replay Framework

模型加速/模型压缩（已完成所有Lab）

ntype cafe summer school resources

课程pdf以及ipynb以及学习笔记

All Homeworks for TinyML and Efficient Deep Learning Computing 6.5940 • Fall • 2023 • https://efficientml.ai

Penn CIS 5650 (GPU Programming and Architecture) Final Project

LLM training in simple, raw C/CUDA

深度学习系统笔记，包含深度学习数学基础知识、神经网络基础部件详解、深度学习炼丹策略、模型压缩算法详解。

Box64 - Linux Userspace x86_64 Emulator with a twist, targeted at ARM64 Linux devices

[IEEE T-PAMI 2024] All you need for End-to-end Autonomous Driving

《动手学大模型Dive into LLMs》系列编程实践教程

A Fast and Extensible DRAM Simulator, with built-in support for modeling many different DRAM technologies including DDRx, LPDDRx, GDDRx, WIOx, HBMx, and various academic proposals. Described in the…

LLM101n: Let's build a Storyteller

模型部署白皮书(CUDA|ONNX|TensorRT|C++)🚀🚀🚀

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

QEMU with support for CHERI

High-performance QEMU memory and instruction tracing

how to optimize some algorithm in cuda.

compiler learning resources collect.

Summary for Stanford class CS243 - Program Analysis and Optimizations | Winter 2016

Clone this repo to build Frida

revng: the core repository of the rev.ng project

A categorized list of C++ resources.

A high performance LLVM-based dynamic binary instrumentation framework

Lift machine code to performant LLVM IR