微信内可能无法直接打开本站。请点右上角 ··· → 在浏览器打开，或复制链接。
Data-Driven Dynamic Algorithm Dispatch with Large Language Models
RSS 官方收录 · 可信分层展示
关键摘要
arXiv:2608.…
- 21584v1 Announce Type: new Abstract: We introduce a large language mod…
- By combining prompt engineering with LLaMA 3 and a curated performance…
- A case study on LU factorization demonstrates the model's ability to r…
摘要引擎：抽取
正文提要
arXiv:2608.21584v1 Announce Type: new Abstract: We introduce a large language model (LLM)-driven approach for generating dynamic algorithmic dispatch heuristics in high-performance linear algebra. By combining prompt engineering with LLaMA 3 and a curated performance database, the model learns to synthesize selection heuristics that exploit structural patterns to identify fast algorithmic choices. A case study on LU factorization demonstrates the model's ability to replicate expert-designed strategies. This work, developed as part of the DARPA-MIT SmartSolve project, highlights the promise of LLMs for algorithmic discovery and the development of more adaptive, fast linear algebra software.