TensorRT 11.1 推出全局性能调优器，突破单一构建路径
原标题：Scaling NVIDIA TensorRT Performance Optimization Beyond a Single Build Route with the Global Performance Tuner, Part 1
AI 摘要
NVIDIA 在技术博客中介绍 TensorRT 11.1 新增的 Global Performance Tuner 功能，用于自动性能调优。文章指出，TensorRT 编译引擎时的调度决策（图变换、融合、实现选择、内存布局、量化）相互耦合，单一启发式策略难以适配所有模型，导致启发式规则膨胀、性能与精度纠缠、定制化困难三类问题。文章用厨师调味的类比和数学框架说明调优是启发式优化的可扩展补充，并预告第二部分。
正文节选
Deploying a trained neural network involves more than translating each operator into a GPU kernel. It is a compilation problem with many legitimate answers. For example, when NVIDIA TensorRT builds an engine, it makes interdependent decisions about graph-IR transformations, fusion, implementation selection, memory placement, and quantization. This process is called scheduling. Different scheduling choices can preserve model semantics yet produce very different inference performance, making sched