NVIDIA TensorRT 如何用 Global Performance Tuner 突破单一构建路径的性能优化限制（上）
Scaling NVIDIA TensorRT Performance Optimization Beyond a Single Build Route with the Global Performance Tuner, Part 1
NVIDIA TensorRT 构建引擎时需在计算图变换、融合、实现选择、内存布局与量化上做相互依赖的调度决策，单一构建路径难以覆盖所有最优解。Global Performance Tuner 用于把性能优化扩展到单一构建路径之外，本篇为上篇。
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...
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.
来源：NVIDIA Technical Blog · developer.nvidia.com