NVIDIA TensorRT 11.1 Global Performance Tuner 如何突破单一构建路径实现性能优化（第二部分）
Scaling NVIDIA TensorRT Performance Optimization Beyond a Single Build Route with the Global Performance Tuner, Part 2
NVIDIA TensorRT 11.1 引入的 Global Performance Tuner 是一项自动性能调优功能，可在 TensorRT 内针对不同模型定制不同优化，实现精度感知的端到端调优。该系列第二部分继续探讨如何突破单一构建路径的性能优化限制，第一部分已介绍深度学习调度阶段的挑战。
The Global Performance Tuner is a feature for automatic performance tuning released in NVIDIA TensorRT 11.1. It provides automatic, accuracy-aware and...
The Global Performance Tuner is a feature for automatic performance tuning released in NVIDIA TensorRT 11.1. It provides automatic, accuracy-aware and end-to-end performance tuning within TensorRT by customizing different optimizations for different models. For more details, see Part 1 of this series, which introduces the challenges associated with scheduling (a critical stage in deep learning…
来源：NVIDIA Technical Blog · developer.nvidia.com