NVIDIA releases new features
The story so far
NVIDIA has released the Global Performance Tuner (GPT) for NVIDIA TensorRT 11.1, extending single-build optimization capabilities. GPT can automatically perform precision-aware end-to-end performance tuning, automatically adjusting different optimization strategies within TensorRT by customizing optimization plans for different models. Previously, deploying trained neural networks was considered a compilation problem with multiple valid solutions.
AI-written from the reports · Updated 26 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- NVIDIA Technical BlogScaling NVIDIA TensorRT Performance Optimization Beyond a Single Build Route with the Global Performance Tuner, Part 2
NVIDIA's Global Performance Tuner (GPT) introduced in TensorRT 11.1 can automatically perform precision-aware end-to-end performance tuning, extending single-build optimization capabilities by customizing optimization solutions for different models. GPT supports automatic adjustment of different optimization strategies within TensorRT.
- NVIDIA Technical BlogScaling NVIDIA TensorRT Performance Optimization Beyond a Single Build Route with the Global Performance Tuner, Part 1
NVIDIA TensorRT schedules interdependent decisions such as graph-IR conversion, fusion, implementation selection, memory layout, and quantization when deploying trained neural networks. The Global Performance Tuner (GPT) enables TensorRT performance optimization beyond a single build path.