Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

各厂家 Coding Plan 实际价值对比

FlyDSL is the Python front‑end of the project: a Flexible Layout Python DSL for expressing tiling, partitioning, data movement, and kernel structure at a high level.

DeepGEMM: clean and efficient BLAS kernel library on GPU

Massively Accelerated Learning of Operators for Quantum-transport

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

Quantum Transport Simulations at the Exascale and Beyond

FAIR Chemistry's library of machine learning methods for chemistry

Lightning fast C++/CUDA neural network framework

ABACUS开源软件的中文用户文档

A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.

An electronic structure package based on either plane wave basis or numerical atomic orbitals.

Productive, portable, and performant GPU programming in Python.

A deep learning package for many-body potential energy representation and molecular dynamics

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

a package for developing machine learning-based chemically accurate energy and density functional models

A deep learning package for many-body potential energy representation and molecular dynamics

CUDA Templates and Python DSLs for High-Performance Linear Algebra

Fast, flexible and easy to use probabilistic modelling in Python.