Habana Developer Blog

/ Developer Blog

Detecting frequent graph re-compilations

In training workloads, there may occur some scenarios in which graph re-compilations occur. This can create system latency and slow down the overall training process with multiple iterations of graph compilation. This blog focuses on ... Read more
debugging, Gaudi, performance, pytorch

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

Sometimes we want to run the same model code using different type of AI accelerators. For example, this can be required if your development laptop has a GPU, but your training server is using Gaudi. Or ... Read more
Gaudi

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

A live demo of Stable Diffusion was presented by Pat Gelsinger in Intel Innovation  in September and there has been a lot of interest from our users since then. With this release, we are publishing ... Read more
synapseai

Fine tuning GPT2 with Hugging Face and Habana Gaudi

In this tutorial, we will demonstrate fine tuning a GPT2 model on Habana Gaudi AI processors using Hugging Face optimum-habana library with DeepSpeed. What is fine tuning? Training models from scratch can be expensive, especially ... Read more
DeepSpeed, Fine Tuning, Gaudi, GPT, GPT2, Hugging Face

Memory-Efficient Training on Habana® Gaudi® with DeepSpeed

One of the key challenges in Large Language Model (LLM) training is reducing the memory requirements needed for training without sacrificing compute/communication efficiency and model accuracy.  DeepSpeed [2] is a popular deep learning software library ... Read more
DeepSpeed, Gaudi, Large Language Models
Sign up for the latest Habana developer news, events, training, and updates.
Sign up