KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta
Authors:
- 1 June 2026
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 733-747
Abstract
No abstract availableAll Related Versions
This publication has 20 references indexed in Scilit:
- Competition-level code generation with AlphaCodeScience, 2022
- Understanding the Power of Evolutionary Computation for GPU Code Optimization2022
- RecPipe: Co-designing Models and Hardware to Jointly Optimize Recommendation Quality and Performance2021
- Understanding Capacity-Driven Scale-Out Neural Recommendation Inference2021
- GEVOACM Transactions on Architecture and Code Optimization, 2020
- GEVO-ML2020
- The Architectural Implications of Facebook's DNN-Based Personalized Recommendation2020
- Triton: an intermediate language and compiler for tiled neural network computations2019
- Genetic Improvement of GPU Code2019
- HalideACM SIGPLAN Notices, 2013