# What is TensorRT? Definition and meaning

A compiler and runtime that optimizes neural networks for NVIDIA GPUs.

## Definition

**TensorRT**: A compiler and runtime that optimizes neural networks for NVIDIA GPUs.

In short: NVIDIA's inference optimizer.

## When it is used

Lowest-latency GPU inference.

## Where it fits

TensorRT belongs to **Inference and serving** in the [MLOps and AI infrastructure](/topics/mlops-ai-infrastructure) topic. These are the other terms in the same group:

- **[Triton](/glossary/triton)**: A server that runs models from many frameworks with dynamic batching and concurrent execution on GPUs.
- **[vLLM](/glossary/vllm)**: An engine that uses PagedAttention and continuous batching to serve language models efficiently.
- **[SGLang](/glossary/sglang)**: A serving framework with efficient prefix caching and a language for structured generation.
- **[ONNX Runtime](/glossary/onnx-runtime)**: A runtime that executes models in the ONNX format across hardware backends.
- **[llama.cpp](/glossary/llama-cpp)**: A library that runs quantized language models on CPUs and a range of GPUs.

## Learn more

The full guide to **[TensorRT](/tools/tensorrt)** explains how it works, when to use it and how it compares with the alternatives, with examples. The [glossary](/glossary) lists every term on the site from A to Z.

Previous term: [TensorFlow](/glossary/tensorflow) · Next term: [Terraform](/glossary/terraform)
