1
Xe-Forge: Multi-Stage LLM-Powered Kernel Optimization for Intel GPU
多阶段LLM流水线自动优化Intel GPU内核，释放硬件潜力，开辟AI驱动编译器新方向
arXiv:2605.26118v1 Announce Type: cross Abstract: Porting deep learning algorithms to new hardware accelerators requires developers to repeatedly appl…