thinQmaster Virtual testing partner Adaptive practice exams that find your weak spots and drill them. Every answer explained. From $69
Enroll

thinQmaster

Find your exam

Five questions free, before you decide.

Step 1 · choose a vendor

In one of our camps? Your practice exams come with the tuition — they are on your study page already.

AI & Machine Learning · Intermediate

TensorRT

NVIDIA's SDK for optimizing trained models into high-performance inference engines.

Definition

TensorRT applies layer fusion, kernel auto-tuning and precision calibration (FP16, INT8, FP8, FP4) to produce GPU-specific engines with lower latency and higher throughput. Models are often imported via ONNX.

Exam tip

TensorRT engines are built for a specific GPU architecture and precision.

Related terms