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

Programmable CUDA/C++ GPU Graph Analytics

MLIR-based partitioning system

PROPELLER: Profile Guided Optimizing Large Scale LLVM-based Relinker

Training and serving large-scale neural networks with auto parallelization.

PyTorch extensions for high performance and large scale training.

Making large AI models cheaper, faster and more accessible

Ongoing research training transformer language models at scale, including: BERT & GPT-2

LingoDB: A new analytical database system that blurs the lines between databases and compilers.

A cross platform way to express data transformation, relational algebra, standardized record expression and plans.

卢瑟们的作业展示，答案讲解，以及一些C++知识

A list of bugs found by SQLancer

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

2025届互联网校招信息汇总

Material for gpu-mode lectures

A retargetable MLIR-based machine learning compiler and runtime toolkit.

A lightweight memory allocator for hardware-accelerated machine learning

Keep your bugs contained. A platform for studying historical software bugs.

“Debian 小药盒”，一个用来包装 Debian 安装介质的盒子设计和介绍用的说明书。

A massively parallel, optimal functional runtime in Rust

💥💻💥 A data-parallel functional programming language

A massively parallel, high-level programming language

Training materials provided by OpenACC.org.

C/C++ frontend for MLIR. Also features polyhedral optimizations, parallel optimizations, and more!

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

NO TIME TO SLEEP

Tile primitives for speedy kernels

Hands-On Practical MLIR Tutorial

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

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