Lei Wang Claim this profile

Domain-specific language designed to streamline the development of high-performance GPU/CPU kernels

Open deep learning compiler stack for cpu, gpu and specialized accelerators

NVDLA (An Opensource DL Accelerator Framework) implementation on FPGA.

A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.

帮助大家进行FPGA的入门，分享FPGA相关的优秀文章，优秀项目

《智能计算系统 AI Computing Systems》习题答案、实验答案、课程笔记

play gemm with tvm

GPTQ inference TVM kernel

No description.

Use FPGA to Transfer Image with Gigabits Ethernet

A easy general acc.

Tutorials of Extending and importing TVM with CMAKE Include dependency.

some sample caffemodel, prototxt, test images and pre compiled loadabes .

A NVDLA Loadable Parser.

Tools and Tutorials for IC Card Crack.

GPU Implementation of T-MAC

No description.

No description.

No description.

No description.

用Vuetify.js+Vue.js+Node.js(KOA 自己撸一个博客。http://leiblog.wang

No description.

No description.

zhengfang academic affairs system spider with egg.js

Example project use xadc with E-element ego1 board, read the resistance of the potentiometer.

A high-throughput and memory-efficient inference and serving engine for LLMs

Build and Train AlexNet with PyTorch and Predict with TVM and Pytorch, compare the performance between them

Transactional Verilog design and Verilator Testbench for a RISC-V TensorCore Vector co-processor for reproducible linear algebra

Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab Repositories

A list of tutorials, paper, talks, and open-source projects for emerging compiler and architecture

No description.

some so large project .

🐍🐍🐍kali linux审计系统工具使用方法

🚀 Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

No description.

在MacBook2019上优化gemm.

A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer

No description.

台湾大学李宏毅老师机器学习

NVDLA SW

How To Ask Questions The Smart Way 《提问的智慧》中文版

Tengine is a lite, high performance, modular inference engine for embedded device

No description.

FlashMLA: Efficient MLA decoding kernels

An MLIR-Based Ideas Landing Project

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

Pytorch implement of Auto-Encoder with MNIST dataset.

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

Antares: an automatic engine for multi-platform kernel generation and optimization. Supporting CPU, CUDA, ROCm, DirectX12, GraphCore, SYCL for CPU/GPU, OpenCL for AMD/NVIDIA, Android CPU/GPU backends.

A framework for few-shot evaluation of language models.

CUDA Templates for Linear Algebra Subroutines

本文原文由知名 Hacker Eric S. Raymond 所撰寫，教你如何正確的提出技術問題並獲得你滿意的答案。

No description.

Transfer data over UDP with a Zedboard. This is an example project that transmits and receives data over UDP.

A collection of useful .gitignore templates

Python Productivity for ZYNQ

A collection of Master XDC files for Digilent FPGA and Zynq boards.

School projects from CS211 - Computer Architecture. PA1 - Intro to C Programming. PA2 - Hexadoku Solver and Intro to Machine Learning. PA3 - Binary Bomb Lab. PA4 - Cache Simulator. PA5 - Circuit Simulator.

VGG19 and VGG16 on Tensorflow

Njtech EE Project3.1, HDB3 Encoder and Decoder.

A demo for accelerating YOLOv2 in xilinx's fpga pynq/zedboard

A next generation Python CMake adaptor and Python API for plugins

No description.

No description.

FlashInfer: Kernel Library for LLM Serving

Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

Fast Matrix Multiplications for Lookup Table-Quantized LLMs

No description.

OSDI 2023 WElder artifacts

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

No description.

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

No description.

Faster 3bit CUDA Kernel for gptq.

Compute Shader Playground with DirectX12

Python package built to ease deep learning on graph, on top of existing DL frameworks.

miHoYo APP Genshin Impact daily bonus by Github Action 利用.Net5 和 Github Action 自动执行 米游社原神每日签到福利

☁️ A fast & light & lovely theme for Hexo. 一个对可爱自以为是的 Hexo 主题。

bak of flw repo. nvdla decipter

Join the GitHub Graduation Yearbook and "walk the stage" on June 5.

Migrating from Theano to Tensorflow using Lenet as a case study.

douban movie info crawler made with egg.js.

some shell code for batch video file transcode, powered with ffmpeg

[closed] uni-app project used to make a cloth appointment.

OneBot 标准：一个聊天机器人应用接口标准

Njtech EE Project3.4 DTMF Encode, with stm32f407 chip.

Github profile

Compilers Principles, Techniques, & Tools (purple dragon book) second edition exercise answers. 编译原理（紫龙书）第2版习题答案。

Intellisense engine for Vim8 & Neovim, full language server protocol support as VSCode

🙃 A delightful community-driven (with 1500+ contributors) framework for managing your zsh configuration. Includes 200+ optional plugins (rails, git, OSX, hub, capistrano, brew, ant, php, python, etc), over 140 themes to spice up your morning, and an auto-update tool so that makes it easy to keep up with the latest updates from the community.