NVIDIA
Inference compiler and runtime family that optimises models for NVIDIA GPUs, including Jetson.
TensorRT is NVIDIA's ecosystem of inference compilers and runtimes, covering the core compiler, TensorRT-LLM, the Model Optimizer, TensorRT for RTX and TensorRT Cloud. It applies graph optimisation, layer fusion and FP16 or INT8 precision calibration to reduce latency.
Jetson device, workstation or GPU server
Specifications taken from current manufacturer documentation and last checked on 2026-09-08.
Source: manufacturer documentation
Specifications are summarised from publicly published manufacturer material and are provided for orientation only. Always confirm current figures directly with the manufacturer before purchasing or designing in.
Official Jetson software stack combining the Linux board support package with CUDA-accelerated AI libraries.
Apache 2.0 licensed toolkit for optimising and deploying inference across Intel CPUs, GPUs and NPUs.
MIT-licensed cross-platform inference accelerator with hardware-specific execution providers.