1 रिपॉजिटरी
Automated discovery of high-performance GPU kernels by evolving code based on execution performance.
Distinguishing note: Unlike candidates that provide specific kernel types, this is about the evolutionary process of creating them.
Explore 1 awesome GitHub repository matching operating systems & systems programming · GPU Kernel Evolution. Refine with filters or upvote what's useful.
OpenEvolve is an open-source framework for evolutionary computation that uses language models to drive automated optimization across multiple domains. It can evolve system prompts for large language models, refine source code across programming languages, search for optimal GPU kernel configurations, discover interpretable mathematical expressions from data, and maintain diverse populations of high-performing solutions. The framework integrates multiple evolutionary strategies, including MAP-Elites diversity mapping and island-based topologies, to avoid premature convergence and preserve a wid
An automatic optimizer that uses evolutionary algorithms to find the fastest GPU kernel implementations for neural network operations.