optimum-rbln 0.1.9

Optimum RBLN is the interface between the Hugging Face Transformers and Diffusers libraries and RBLN accelerators. It provides a set of tools enabling easy model loading and inference on single and multiple rbln device settings for different downstream tasks.

Optimum RBLN

🤗 Optimum RBLN is the interface between the 🤗 Transformers library and RBLN Accelerators including ATOM and REBEL. It provides a set of tools enabling easy model loading and inference on single- and multi-Accelerator settings for different downstream tasks. The list of officially validated models and tasks is available here. Users can try other models and tasks with only few changes.

Install from PyPI

To install the latest release of this package:

• Export environment variables to access to RBLN private PyPI.

  export REBEL_PYPI_USERNAME=<username>
  export REBEL_PYPI_PASSWORD=<password>
  

• Install optimum-rbln package:

  pip install --index-url https://pypi.rebellions.in/simple optimum-rbln
  

Install from source

Prerequisites

• Install PDM (refer this link for detailed commands)

The below command installs optimum-rbln along with its dependencies.

git clone https://github.com/rebellions-sw/optimum-rbln.git
cd optimum-rbln
pdm install

To install optional dependencies from all groups, specify -G:all option.

pdm install -G:all

If you want to install optimum-rbln as editable mode in existing venv,

(venv) pip install -e .

How to use it?

Quick Start

🤗 Optimum RBLN was designed with one goal in mind: to make inference straightforward for any 🤗 Transformers user while leveraging the complete power of RBLN Accelerators.

Documentation

Check out the documentation of Optimum RBLN for more advanced usage.