🔥LeetCode solutions in any programming language | 多种编程语言实现 LeetCode、《剑指 Offer（第 2 版）》、《程序员面试金典（第 6 版）》题解

[MLSys 2021] IOS: Inter-Operator Scheduler for CNN Acceleration

autoTVM神经网络推理代码优化搜索演示，基于tvm编译开源模型centerface，并使用autoTVM搜索最优推理代码，　最终部署编译为c++代码，演示平台是cuda，可以是其他平台，例如树莓派，安卓手机，苹果手机．Thi is a demonstration of how to use autoTVM to search and optimize a neural network i…

TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.

Open deep learning compiler stack for Kendryte AI accelerators ✨

The road to hack SysML and become an system expert

BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.

Extending and Modifying LAMMPS中文翻译

flash attention tutorial written in python, triton, cuda, cutlass

optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052

TileGraph is an experimental DNN compiler that utilizes static code generation and kernel fusion techniques.

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

Puzzles for learning Triton

System for AI Education Resource.

Allegro is an open-source code for building highly scalable and accurate equivariant deep learning interatomic potentials

NequIP is a code for building E(3)-equivariant interatomic potentials

SevenNet - a graph neural network interatomic potential package supporting efficient multi-GPU parallel molecular dynamics simulations.

An ML Systems Onboarding list

Material for gpu-mode lectures

A New Format for SIMD-accelerated SpMV

aria2 is a lightweight multi-protocol & multi-source, cross platform download utility operated in command-line. It supports HTTP/HTTPS, FTP, SFTP, BitTorrent and Metalink.

[CVPR'23] FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer

play gemm with tvm

BLISlab: A Sandbox for Optimizing GEMM

pytorch模板，简化并规范模块编写