Welcome to Habana’s developer site.

Here you will find the content, guidance, tools and support needed to easily and flexibly build new or migrate existing AI models and optimize their performance to meet your AI requirements. You can also access the latest Gaudi software to build or update your infrastructure. 

Habana Labs announced the Gaudi2 processor for training deep learning workloads

Learn about Gaudi2

Fast Inference on Large Language Models: BLOOMZ. Easily deploy multi-billion parameter language models on Habana Gaudi2.

Read the Blog

We’re excited to introduce the release of Habana® SynapseAI® Software version 1.13.0

Learn more

Get Started

Get access to Habana’s programmable Tensor Processor Core and SynapseAI® software stack with support for TensorFlow and PyTorch frameworks, along with our model garden, libraries, containers and tools that enable you to build popular AI models. Now supporting the new Gaudi®2 Processor!

Resources

Get detailed technical guides to start running models on Gaudi2 and our first-gen Gaudi Processors.

Go to Resources

Generative AI & Large Language Models

Learn more about training and inference of large scale and foundation models on Habana Gaudi.

Get started

Cloud

Learn how to setup and run your instances in the cloud using Amazon EC2 DL1 Training Instances or the Intel Developer Cloud.

Get started

Software Setup and Installation 

Install the latest SynapseAI® Software, including Habana’s graph compiler and runtime, TPC kernel library, firmware and drivers, and tools. 

Setup and Install

Model Performance Data

Access Habana’s popular model performance data for Gaudi2 and our First-gen Gaudi Processor

Learn more

Habana GitHub

Access reference models, support roadmap, and more.

Habana GitHub
Sign up for the latest Habana developer news, events, training, and updates.
Sign up

Latest Webinar Recordings and Informative ‘How To’ Videos

Learn and explore at your own pace with our on-demand webinars and easy-to-follow ‘How To’ videos.

Maximizing the Power of Gaudi2: Accelerating Generative AI and Large Language Models

BLOOM Z

Gaudi2 on 176 Billion Parameter BLOOMZ

events-featured

Getting Started with Habana: Deep Learning and Inference on Gaudi

Scale systems with a single-card to thousands of Gaudi2s

Recent Posts and Tutorials

Check out these latest posts from our blog. 
post

Fine-Tuning Llama2-70B with DeepSpeed ZeRO-3 and Low-Rank Adaptation (LoRA) on Intel® Gaudi®2 AI Accelerator

With Habana’s SynapseAI 1.13.0 release, users can run Fine Tune the Llama2 70B model using only 8 Gaudi2 Accelerators.
Read more
DeepSpeed, Fine Tuning, Llama, LoRA
post

We’re excited to introduce the release of Habana® SynapseAI® Software version 1.13.0

Bringing forth numerous enhancements and updates for an improved user experience.
Read more
synapseai
tutorials

Using LocalGPT with Llama2

Using LocalGPT on Intel® Gaudi®2 AI accelerators with the Llama2 model to chat with your local documentation
Read more
tutorials

Llama2 Fine-Tuning with Low-Rank Adaptations (LoRA) on Intel® Gaudi®2 AI Accelerator

Fine-tune Llama2 more efficiently with Low-Rank Adaptations (LoRA) on Intel Intel Gaudi2 AI accelerators
Read more
Go to the blog
Sign up for the latest Habana developer news, events, training, and updates.
Sign up