PassNet: Scaling Large Language Models for Graph Compiler Pass Generation 事件

PassNet: Scaling Large Language Models for Graph Compiler Pass Generation arXiv:2605.29357v1 Announce Type: new Abstract: Modern tensor compilers such as TorchInductor deliver substantial speedups on mainstream models, yet face a systematic performance ceiling on long-tail workloads -- our profiling shows that 43% of real-world subgraphs experience end-to-end slowdowns under default compilation. While LLMs offer a path toward automated optimization, existing efforts focus on standalone kernel g