NVIDIA TensorRT 11.1 的全局性能调优器（GPT）扩展单次构建优化能力
Scaling NVIDIA TensorRT Performance Optimization Beyond a Single Build Route with the Global Performance Tuner, Part 2
NVIDIA 在 TensorRT 11.1 中推出的全局性能调优器（GPT）可自动进行精度感知的端到端性能调优，通过为不同模型定制优化方案扩展了单次构建优化能力。GPT 支持在 TensorRT 内部自动调整不同优化策略。
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