Inference CLI¶

Roboflow Inference CLI is a command-line interface for the inference ecosystem, providing an easy way to:

• run and manage inference server locally
• process data with Workflows
• benchmark inference performance
• make predictions from your models
• deploy inference server in cloud

Installation¶

pip install inference-cli

Note that if you have installed the inference Python package, the CLI extensions are already included.

Supported Devices¶

Roboflow Inference CLI currently supports the following device targets:

• x86 CPU
• ARM64 CPU
• NVIDIA GPU (including Jetson)

For Jetson specific inference server images, check out the Roboflow Inference package, or pull the images directly following instructions in the official Roboflow Inference documentation.