Home » Content Directory

Content Directory

Listed below are some of the helpful links that will easily help you find resources and content needed to get started with Intel Gaudi.

Blog posts

We’re excited to introduce the release of Intel® Gaudi® software version 1.17.0

Intel Gaudi Software

We’re excited to introduce the release of Intel® Gaudi® software version 1.16.0

Intel Gaudi Software

Building Cost-Efficient Enterprise RAG applications with Intel Gaudi 2 and Intel Xeon

Gaudi2, Large Language Models, RAG

Leveraging Intel Gaudi for Distributed Training with FSDP

FDSP, Gaudi2, Intel Gaudi Accelerators

We’re excited to introduce the release of Intel® Gaudi® software version 1.15.0

Intel Gaudi Software, synapseai

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

DeepSpeed, Fine Tuning, Llama, LoRA

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

synapseai

Training Llama and Bloom 13 Billion Parameter LLMs with 3D Parallelism on Habana® Gaudi2®

3D-Parallelism, DeepSpeed, GenAI, Large Language Models

Porting a model to Megatron-DeepSpeed with Habana Gaudi

DeepSpeed, GenAI, Large Language Models

Optimizing Large Language Model Inference on Gaudi2 with Hugging Face Optimum-Habana

DeepSpeed, Hugging Face, Inference

The Habana team is happy to announce the release of Habana® SynapseAI® Software version 1.11.0.

synapseai

Accelerate Llama 2 with Intel AI Hardware and Software Optimizations

Deep Learning, Gaudi2, Large Language Models

New MLCommons Results Highlight Impressive Competitive AI Gains for Intel

Gaudi2, MLPerf

Habana® Gaudi®2 Powers Deep Learning Instances on Genesis Cloud at Collision 2023

Gaudi2

The Habana team is happy to announce the release of Habana® SynapseAI® Software version 1.10.0.  

synapseai

Habana Showcases Gaudi2 Performance on Large Language and Generative AI Models at ISC

Gaudi2, Large Language Models

Equus Lab-as-a-Service with Habana Gaudi2 Processors Eases Testing and Deployment of Deep Learning Systems

Gaudi2

Detecting frequent graph re-compilations

debugging, Gaudi, performance, pytorch

New Habana Autonomous Driving Use Case Enabled with Gaudi Processors

Gaudi2, Semantic Segmentation, Training

The Habana team is happy to announce the release of SynapseAI® Software version 1.9.0.

synapseai

Fast Inference on Large Language Models: BLOOMZ on Habana Gaudi2 Accelerator

Gaudi2

Accelerating Distributed Training Performance using EFA Peer Direct on Gaudi-Based AWS EC2 DL1 Instances

Gaudi2

New Habana AI Retail Use Case Enables Automated Store Shelf Management with Gaudi Processors

Gaudi2

Faster Training and Inference: Habana Gaudi®-2 vs Nvidia A100 80GB

Gaudi2, Hugging Face

BLOOM 176B Inference on Habana Gaudi2

BLOOM, DeepSpeed, Inference

White Paper: Riken Accelerates Medical and Drug Research with Habana Gaudi AI Processor

habana.ai

The Habana team is happy to announce the release of SynapseAI® Software version 1.8.0

synapseai

Road sign detection using Transfer Learning with TensorFlow EfficientDet-D0

EfficientDet, Transfer Learning

Pre-Training the BERT 1.5B model with DeepSpeed

BERT, DeepSpeed, Gaudi, Gaudi2, pytorch, synapseai

Eitan Medina – Video Interview – Cambrian AI Research

habana.ai

Enabling DeepSpeed on Gaudi

Training Causal Language Models on SDSC’s Gaudi-based Voyager Supercomputing Cluster

Art Generation with PyTorch Stable Diffusion and Habana Gaudi

Gaudi, pytorch

Writing training scripts that can run either on Gaudi, GPU, or CPU

Gaudi

Habana this week at re:Invent ‘22

habana.ai

The Habana team is happy to announce the release of SynapseAI® version 1.7.0.  

synapseai

Habana this week at Supercomputing ‘22

habana.ai

Habana Gaudi2 makes another performance leap on MLPerf benchmark

habana.ai

Fine tuning GPT2 with Hugging Face and Habana Gaudi

DeepSpeed, Fine Tuning, Gaudi, GPT, GPT2, Hugging Face

Habana Deep Learning Solutions Support OCP OAM Specification

habana.ai

Memory-Efficient Training on Habana® Gaudi® with DeepSpeed

DeepSpeed, Gaudi, Large Language Models

Habana Collaborates with Red Hat to Make AI/Deep Learning More Accessible

Customer Cases

Collaboration with Colossal-AI in providing high-performance, high-efficiency acceleration for protein folding prediction.

AWS Customer Case – Leidos Improves Patient Outcomes Using Amazon EC2 DL1 Instances

AWS Customer Case – Mobileye Improves Deep Learning Training Performance and Reduces Costs Using Amazon EC2 DL1 Instances

SDSC Customer Case – SDSC Builds AI-Focused “Voyager” Supercomputer

Videos

Getting Started with Intel® Gaudi® AI accelerators

GPU Model Migration

Hugging Face Tutorial

Gaudi2 on 176 Billion Parameter BLOOMZ

Scale systems with a single-card to thousands of Gaudi2s

Getting Started with Gaudi: System Setup

Gaudi: Intro to TPC Kernels

Tutorials

Retrieval Augmented Generation (RAG) Application

VisualQnA

SearchQnA

DocSum

CodeGen

ChatQnA

Using LocalGPT with Llama2

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

Profiling and Optimization

Detecting Dynamic Shapes

Inference on Gaudi solutions with HPU Graph

Large Model usage with minGPT

Getting started with AWS DL1 and PyTorch 

Accelerate Transformer training with Optimum Habana

Getting Started with Hugging Face Transformers

Use an HPU

Finetune Transformers Models with PyTorch Lightning

Introduction To PyTorch Lightning

PyTorch Mixed Precision

Distributed Training Using TensorFlow and Horovod

Distributed Training Using TensorFlow and HPUStrategy

Data Packing Process for MLPERF BERT

Intro to Autoencoders

Training a Classifier

Mixed precision

Quick Start

Webinars

Maximizing the Power of Intel Gaudi2 AI Accelerators for Generative AI and Large Language Models

Maximizing Model Performance with Habana Gaudi Processors: Advanced Tools and Strategies for Optimal Results

Live Webinar: Build & Deploy Deep Learning Infrastructure with Equus and Habana Gaudi2 Accelerators

Getting Started with Habana: Deep Learning and Inference on Gaudi

Getting Started with Habana: Deep Speed Optimization on Large Models

On Demand: Getting Started with Habana: Deep Speed Optimization on Large Models

On Demand: Getting Started with Habana: Deep Learning and Inference on Gaudi

Workshop: Getting Started with Habana: Deep Learning on Gaudi

Webinar: Leverage DeepSpeed to Train Faster and Cheaper Large Scale Transformer Models with Hugging Face and Habana Labs Gaudi

Accelerate Transformer Model Training with Hugging Face and Habana Labs

On-Demand: Enhance your on-premises AI capabilities with Habana Labs and DDN

Webinar Series: Profiling and optimizing your model on Habana Gaudi

On Demand: PyTorch on Habana Gaudi
Part 2: Model Migration, Distributed Training, and Profiling

On Demand: PyTorch on Habana Gaudi
Part 1: Model Migration, Distributed Training, and Profiling

On Demand: TensorFlow on Habana Gaudi
Part 2: Model Migration, Distributed Training, and Profiling

On Demand: TensorFlow on Habana Gaudi
Part 1: Model Migration, Distributed Training, and Profiling

On Demand: Getting started with Intel Gaudi AI Processors

Stay Informed: Register for the latest Intel Gaudi AI Accelerator developer news, events, training, and updates.
Sign up