---
format: "aidr-story-markdown/v1"
id: "7383f2fa84171fd11edce71b3f9a06da6d896695b2aab3f0a6ac840a7cf0159a"
canonical_url: "https://aidr.today/7383f2fa?lang=en"
title: "Scaling NVIDIA TensorRT Performance Optimization Beyond a Single Build Route with the Global Performance Tuner, Part 2"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-23T17:27:52.000Z"
category: "Frameworks"
topics: ["nvidia","inference","framework"]
source_urls: ["https://developer.nvidia.com/blog/scaling-nvidia-tensorrt-performance-optimization-beyond-a-single-build-route-with-the-global-performance-tuner-part-2/","https://developer.nvidia.com/blog/scaling-nvidia-tensorrt-performance-optimization-beyond-a-single-build-route-with-the-global-performance-tuner-part-1/"]
summary: "The Global Performance Tuner, introduced in NVIDIA TensorRT 11.1, provides automatic, accuracy-aware, end-to-end performance tuning by representing alternative scheduling strategies as searchable build routes composed of compiler knob values."
---

# Scaling NVIDIA TensorRT Performance Optimization Beyond a Single Build Route with the Global Performance Tuner, Part 2

> [Open the canonical story](<https://aidr.today/7383f2fa?lang=en>)

**Published:** 2026-10-23T17:27:52.000Z
**Category:** Frameworks
**Topics:** nvidia, inference, framework

## Summary

The Global Performance Tuner, introduced in NVIDIA TensorRT 11\.1, provides automatic, accuracy\-aware, end\-to\-end performance tuning by representing alternative scheduling strategies as searchable build routes composed of compiler knob values\.

## Sources

- [Story source](<https://developer.nvidia.com/blog/scaling-nvidia-tensorrt-performance-optimization-beyond-a-single-build-route-with-the-global-performance-tuner-part-2/>)
- [Story source](<https://developer.nvidia.com/blog/scaling-nvidia-tensorrt-performance-optimization-beyond-a-single-build-route-with-the-global-performance-tuner-part-1/>)