Accelerate your models with 🤗 Optimum Intel and OpenVINO

📰 Hugging Face Blog

Hugging Face's Optimum Intel now supports Intel OpenVINO for accelerated model inference and quantization

intermediate Published 2 Nov 2022

Action Steps

Install Optimum Intel and OpenVINO
Use OVModels for inference on Intel processors
Apply post-training static quantization or quantization aware training to encoder models
Host and deploy models on the Hugging Face hub or locally

Who Needs to Know This

Data scientists and machine learning engineers can benefit from this integration to optimize their models for better performance and efficiency

Key Insight

💡 Optimum Intel's integration with OpenVINO enables easy inference and quantization of Transformer models on Intel processors