Skip to main content

Run AI models smashed by Pruna AI

Project description

Pruna Engine

Pruna Engine is a Python package providing the capability of running deep learning models optimized through Pruna AI.

Installation

You can install Pruna Engine via pip from PyPI:

CPU

pip install pruna-engine

GPU

pip install pruna-engine[gpu] --extra-index-url https://pypi.nvidia.com --extra-index-url https://pypi.ngc.nvidia.com

Requirements

  • You need CUDA 12 to be installed on your machine for the GPU version
  • You need to have CUDA toolkit installed on your machine. If you are using a conda environment you can do this by running:
conda install nvidia/label/cuda-12.1.0::cuda
  • We support python 3.8, 3.9, or 3.10

Usage

Here is a simple example of how to use Pruna Engine with a ResNet50 optimized model:

from pruna_engine.PrunaModel import PrunaModel

# And 'your_api_key' is your actual API key
your_api_key = 'test'
smashed_model = PrunaModel.load_model('resnet50_model', your_api_key)
# Run prediction
y = smashed_model(x)

License

All Rights Reserved

Copyright 2023 Pruna AI

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

pruna_engine-0.5.2-py310-none-any.whl (109.3 kB view hashes)

Uploaded Python 3.10

pruna_engine-0.5.2-py39-none-any.whl (108.4 kB view hashes)

Uploaded Python 3.9

pruna_engine-0.5.2-py38-none-any.whl (108.2 kB view hashes)

Uploaded Python 3.8

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page