Wan Youwen

GPU-Tutorials. Tutorials to GPU programming. Reading notes.

FastGEMV. High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.

CuAssembler. An unofficial cuda assembler, for all generations of SASS, hopefully ：）

applied-ai. Applied AI experiments and examples for PyTorch

hifi-gan. HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

wenet. Production First and Production Ready End-to-End Speech Recognition Toolkit

qlora. QLoRA: Efficient Finetuning of Quantized LLMs

docker-ubuntu-desktop. Docker Image for Ubuntu Desktop which support HW GPU accelerated GUI apps. you can access the Container with ssh or remote desktop, just like Cloud VM.

triton. Development repository for the Triton language and compiler

triton. Development repository for the Triton language and compiler

Telechat. Python

self-llm. 《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

OneNeuralNetwork. This is a cross-chip platform collection of operators and a unified neural network library.

gpt-tokens. What are learned in tiktoken?

Learning-Materials-of-SMSE. 清华大学材料学院本科学习资料 - PPT、图书、作业、实验报告等

aipath. AI学习之路

aipath. AI学习之路

pytorch. Ascend PyTorch adapter (torch_npu). Mirror of https://gitcode.com/Ascend/pytorch

Megatron-LM. Python

AscendCL_GEMM. C++

RWKV-CUDA. The CUDA version of the RWKV language model ( https://github.com/BlinkDL/RWKV-LM )

NN-CUDA-Example. Several simple examples for popular neural network toolkits calling custom CUDA operators.

Optimizing-SGEMM-on-NVIDIA-Turing-GPUs. Optimizing SGEMM kernel functions on NVIDIA GPUs to a close-to-cuBLAS performance.

How_to_optimize_in_GPU. This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, sgemv, sgemm, etc. The performance of these kernels is basically at or near the theoretical limit.

ml_toolset. Jupyter Notebook

TheRoadOfSO. 学习安全运营的记录 | The knowledge base of security operation

rebekah. C++开发的视频行为分析系统v5（rebekah）

ESJZone-novel-mirror. ESJZone 的小說備份

trending-in-one. 今日头条热搜,知乎热门视频，知乎热搜榜，知乎热门话题，微博热搜榜；记录从 2020-11-29 日开始的热搜。每小时抓取一次数据，按天归档。

weibo-trending-hot-search. 微博热搜榜，记录从 2020-11-24 日开始的微博热门搜索。每小时抓取一次数据，按天归档。

tiny-gpu. A minimal GPU design in Verilog to learn how GPUs work from the ground up

chatchat-knowledgebase. 属于每个人的公众号”查特查特“上线啦！新问题、新方法、新发现，欢迎提PR！

GroundingDINO. [ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

AI-News-Daily.

isp. camera pipeline

Tutorial. LLM&VLM Tutorial

CSLabInfo2024. 关于2024年CS保研实验室/导师招生广告的汇总。欢迎想要打广告的小伙伴积极PR，资瓷一下互联网精神吼不吼啊？

translations.

nolebase. A place to record memories, knowledge and ideas | 记录回忆，知识和畅想的地方

RT-DETR. Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

Trajectory-Transformer. Code for "Transformer Networks for Trajectory Forecasting"

P2T. Code for "Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Plans" https://arxiv.org/abs/2001.00735

trajnetplusplusbaselines. [ITS'21] Human Trajectory Forecasting in Crowds: A Deep Learning Perspective

STR-PIP. Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction

onnc. Open Neural Network Compiler

devops-super. 基于 golang goframe + vue3 的、前后端分离的运维平台。

Autopilot-Notes. 自动驾驶笔记，以解析各模块知识点、整合行业优秀解决方案进行阐述，以帮助自己及有需要的读者；包含深度学习、deeplearning、无人驾驶、BEV、Transformer、ADAS、CVPR、特斯拉AI DAY、大模型、chatgpt等内容.

net. 互联网体系结构/庖丁解牛Linux网络协议栈

opencv-mobile. The minimal opencv for Android, iOS, ARM Linux, Windows, Linux, MacOS, HarmonyOS, WebAssembly, watchOS, tvOS, visionOS

caj2pdf. Convert CAJ (China Academic Journals) files to PDF. 转换中国知网 CAJ 格式文献为 PDF。佛系转换，成功与否，皆是玄学。

llama.onnx. LLaMa/RWKV onnx models, quantization and testcase

blis. BLAS-like Library Instantiation Software Framework

llama. Inference code for Llama models

xformers. Hackable and optimized Transformers building blocks, supporting a composable construction.

onnx-tool. A tool for parsing, editing, optimizing, and profiling ONNX models.

chatbot. Transformer模型训练的单轮对话聊天机器人

fastapprox. Approximate and vectorized versions of common mathematical functions

fmath. fast log and exp functions for AVX2/AVX-512

tvm_mlir_learn. compiler learning resources collect.

playground. code for fun

Loop-Invariant-Code-Motion. Implemented a LLVM library for loop invariant code motion

linear_operator. A LinearOperator implementation to wrap the numerical nuts and bolts of GPyTorch

AISystem. 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

mshadow. Matrix Shadow:Lightweight CPU/GPU Matrix and Tensor Template Library in C++/CUDA for (Deep) Machine Learning

CSIMD. SIMD Accelerated Operations for Complex Numbers.

tvm-rfcs. A home for the final text of all TVM RFCs.

FileCheck.py. [PROJECT DISCONTINUED] See the newer https://github.com/AntonLydike/filecheck.

movenet. Google's Next Gen Pose Estimation in PyTorch

V2V-PoseNet_Pytorch. human pose estimation

V2V-PoseNet_RELEASE. Official Torch7 implementation of "V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map", CVPR 2018

ccf-deadlines. ⏰ Agenticly track worldwide conference deadlines (Website, Python Cli, Wechat Applet)

libfacedetection. An open source library for face detection in images. The face detection speed can reach 1000FPS.

trusting-trust-demo-and-defense. C

onnx_optimize. post process of onnx model which converted from torch(Enet, centernet)

backward-cpp. A beautiful stack trace pretty printer for C++

ivy. Convert Machine Learning Code Between Frameworks

graph_dsl. An demo for spatial computing

c-mlir. A translator from c to MLIR

ElectronBot. C

llvm-tutor. A collection of out-of-tree LLVM passes for teaching and learning

second.pytorch. PointPillars for KITTI object detection

learn-python3. Learn Python 3 Sample Code

Cpp_Concurrency_In_Action. :book: 作为对《C++ Concurrency in Action》英文版的中文翻译。

license-plate-detect-recoginition-pytorch. 深度学习车牌检测与识别，检测结果包含车牌矩形框和4个角点，基于pytorch框架运行

state-of-the-art-shitcode. 💩State-of-the-art shitcode principles your project should follow to call it a proper shitcode

rgbdslam_v2. RGB-D SLAM for ROS

DeepBench. Benchmarking Deep Learning operations on different hardware

persistent-rnn. Fast Recurrent Networks Library

treelstm. Tree-structured Long Short-Term Memory networks (http://arxiv.org/abs/1503.00075)

AutoDL-Projects. Automated deep learning algorithms implemented in PyTorch.

code_comment_generation. Automatic Generation of Text Descriptive Comments for Code Blocks

blog. A front-end blog | 前端博客

vectry. Simple vector math library for any purposes

cmake-stm32. Basic CMake project for STM32

vcxproj-generator. vcxproj generator

slambook. C++

self-driving-car. Udacity Self-Driving Car Engineer Nanodegree projects.

movingCatchRobot. a robot with bottom moving platform of dashgo and a mechanical arm of dobot, running ROS in x86 minipc

Caffers. 一个小型命令行日记软件，采用问答模式书写日记

movec. Movec: A Tool for the Monitoring and Verification of C Programs

ml-compiler-opt. Infrastructure for Machine Learning Guided Optimization (MLGO) in LLVM.

algo. 数据结构和算法必知必会的50个代码实现

testdemo. Python

leetcode-java. LeetCode solutions written in Java

benchmark. A microbenchmark support library

Hands-On-Design-Patterns-with-CPP. Hands-On Design Patterns with C++, published by Packt

EigenChineseDocument. This is my translation of Chinese document of Eigen

blitzscaling. cs183c 斯坦福创业课程

BoolanStudy. 在博览网上上课的资料

C-C-. 程序员相关电子书资料免费分享，欢迎关注个人微信公众号：编程与实战

ArduinoDMX. C++

Vis. Interactive & Asynchronous 3D Visualization Tool

AI-System. System for AI Education Resource.

vi-mode. Shell

leetcode-python-in-one-line. I want to solve Leetcode questions in one line with python

Shengsi-ticket. 嵊泗船票的抢票脚本

Statistical-Learning-Methods. Implement Statistical Learning Methods, Li Hang the hard way. 李航《统计学习方法》一书的硬核 Python 实现

leetcode-racket. Solve leetcode problems by racket.

RacketGuideInChinese. Racket指南（中文翻译）

racket. The Racket repository

gridstudio. Grid studio is a web-based application for data science with full integration of open source data science frameworks and languages.

cnblogs. 一些我在平时工作和学习中积累的编程相关的资源。如果大家有兴趣可以一起增加，修改。

Road2Coding. 编程之路

randprog. Randomly generate a C (or javascript) program

yarpgen. Yet Another Random Program Generator

TASO. The Tensor Algebra SuperOptimizer for Deep Learning

LLVMPascalCompiler. This is the source code of My LLVM Pascal Compiler Tutorial

HiCOND. C++

libfuzzer-workshop. Repository for materials of "Modern fuzzing of C/C++ Projects" workshop.

ast_compare. compare ast via pythn ast library

llvm_CGPass. llvm Call Graph分析

llvm-stack-guard. 简化版本llvm的stackprotector策略，将其包装成一个pass，对程序的stack进行保护

llvm-BBProfiling. llvm pass to profile BasicBlocks' execution path

llvm_CFGPass. llvm control flow graph

fuzzing_paper. fuzzing related paper

ClangKit. ClangKit provides an Objective-C frontend to LibClang. Source tokenization, diagnostics and fix-its are actually implemented.

GameEngineFromScratch. 配合我的知乎专栏写的项目

mydot. my dot files in ubuntu

abi-aa. Application Binary Interface for the Arm® Architecture

ccls. C/C++/ObjC language server supporting cross references, hierarchies, completion and semantic highlighting

localization_in_auto_driving. C++

LLVM_for_cpu0. This is a tutorial to learn LLVM, I realize a backend to compiler machine code for cpu0 which is a simple RISC cpu.

ow. Old work

tac. topics about compilers

nc. npu compiler

lbd. C++

note. my note about IT's commands or language

ex. code example

XNet. Simple CuDNN wrapper

XNet. Simple CuDNN wrapper

pytorch-lightning-template. An easy/swift-to-adapt PyTorch-Lighting template. 套壳模板，简单易用，稍改原来Pytorch代码，即可适配Lightning。You can translate your previous Pytorch code much easier using this template, and keep your freedom to edit all the functions as well. Big-project-friendly as well. No need to rewrite your config in hydra.

Enzyme. High-performance automatic differentiation of LLVM and MLIR.

websocket. A single header c++ websocket client/server lib for linux

smo. A storage optimization tool for regular loop nests

cpdemo. Cython+Pyinstaller Python编译与打包-踩坑示例代码

rust. Empowering everyone to build reliable and efficient software.

yngzmiao-blogs. Blogs content and codes

protobuf-parser-tool. Create/parse proto binary files

Boost-Python-Examples. Implementation of C++ Boost Python Examples, With python3.5+ support

coupons. 美团饿了吗外卖红包外卖优惠券，先领红包再下单。外卖红包优惠券，cps分成，别人领红包下单，你拿佣金。

schools-map. 学区房地图

tvm_tests. Python

relay-aot. An experimental ahead of time compiler for Relay.

Krill. An efficient concurrent graph processing system

tianshou. An elegant PyTorch deep reinforcement learning library.

couplet_generation. generate couplet(对联生成) Tensorflow

Algorithm. 数据结构算法的整理讲解，含Java/Python版本

aided_driving_app. 基于机器视觉的智能辅助驾驶应用，作为系统的移动端衍生，使用Flutter进行开发，适配双端（Android、IOS）

nlp-paper. 自然语言处理领域下的相关论文（附阅读笔记），复现模型以及数据处理等（代码含TensorFlow和PyTorch两版本）

tensorflow-eager-tutorials. Simple tutorials for building neural networks with TensorFlow Eager mode.

tensorflow-internals. It is open source ebook about TensorFlow kernel and implementation mechanism.

TensorFlow-Examples. TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)

gast. Python AST that abstracts the underlying Python version

tensorflow. An Open Source Machine Learning Framework for Everyone

eat_tensorflow2_in_30_days. Tensorflow2.0 🍎🍊 is delicious, just eat it! 😋😋

jax. Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

runtime. A performant and modular runtime for TensorFlow

Image-processing-algorithm. paper implement

ThreadSwitch--Simulation. C++ & inline assemble

ArmNeonOptimization. Arm neon optimization practice

llvm-ustc-proj. Some Clang static analyzers.

Paddle. PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

lightseq. LightSeq: A High Performance Library for Sequence Processing and Generation

Ryven. Flow-based visual scripting for Python

fc_malloc. Super Fast, Lock-Free, Wait-Free, CAS-free, thread-safe, memory allocator.

MetaDSL. A simple language similar to XML/JSON, which can describe both data and logic.

fc. Accelerate your C++ Compiles

existing. Python

Project2019Spring. Main project, Compiler design PKU 2019 Spring

CompilerProject-2020Spring. Course Project. PKU Compiler Design. Spring, 2020.

MAgent. A Platform for Many-Agent Reinforcement Learning

onnx-mlir. Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure

compiler_assignment. compiler assignment testing codes [PKU, Course: Compiler Design, 2019 Spring]

awesome-tensor-compilers. A list of awesome compiler projects and papers for tensor computation and deep learning.

heterocl. HeteroCL: A Multi-Paradigm Programming Infrastructure for Software-Defined Heterogeneous Computing (FPGA'19 Best Paper)

SimpleFPSTemplate. Simple C++ FPS Template for Unreal Engine

FlexTensor. Automatic Schedule Exploration and Optimization Framework for Tensor Computations

ActionRoguelike. Co-op Action Roguelike in Unreal Engine C++

ppcg. Polyhedral Parallel Code Generation (source repository: http://repo.or.cz/ppcg.git)

pluto. Pluto: An automatic polyhedral parallelizer and locality optimizer