Neural Magic LogoNeural Magic Logo
Products
menu-icon
Products
DeepSparse EngineSparseMLSparseZoo
Get Started
Installation
DeepSparse

DeepSparse Community Edition Installation

The DeepSparse Engine enables GPU-class performance on CPUs, leveraging sparsity within models to reduce FLOPs and the unique cache hierarchy on CPUs to reduce memory movement. The engine accepts models in the open-source ONNX format, which are easily created from PyTorch and TensorFlow models.

Currently, DeepSparse is tested on Python 3.7-3.10, ONNX 1.5.0-1.10.1, ONNX opset version 11+ and is manylinux compliant. It is limited to Linux systems running on x86 CPU architectures.

The DeepSparse Engine is available in two editions:

  1. The Community Edition is open-source and free for evaluation, research, and non-production use with our Engine Community License.
  2. The Enterprise Edition requires a Trial License or can be fully licensed for production, commercial applications.

General Installation

Use the following command to install the Community Edition with pip:

pip install deepsparse

Server Install

The DeepSparse Server allows you to serve models and pipelines through an HTTP interface using the deepsparse.server CLI. To install, use the following extra option:

pip install deepsparse[server]

YOLO Install

The Ultralytics YOLOv5 models require extra dependencies for deployment. To use YOLO models, install with the following extra option:

1pip install deepsparse[yolo] # just yolo requirements
2pip install deepsparse[yolo,server] # both yolo + server requirements
Install Deep Sparse Platform
DeepSparse Enterprise Installation