In this video, I show you how to accelerate Stable Diffusion and Stable Diffusion XL inference with the Hugging Face Optimum Neuron library and AWS Inferentia 2. A few lines of code is all it takes, and of course, we run some benchmarks.

In this video, I compare the cost/performance of AWS Trainium with the NVIDIA V100 GPU. I first launch a trn1.32xlarge instance (16 Trainium chips) and a p3dn.24xlarge (8 V100s). Then, I run 3 benchmarks: language pretraining with GPT2, token classification with BERT Large, and image classification with the Vision Transformer. The results? Trainium is 2 to 5x faster, and 3 to 8x cheaper!

In this video, I show how you to accelerate training and inference for Hugging Face models on AWS Trainium and AWS Inferentia2. Thanks to our Optimum Neuron library, a single line of code is all it takes to enjoy amazing cost-performance. Give it a try!

In this session, after a brief intro, I use Hugging Face AutoTrain to train a food image classification model on the food101 dataset. Then, using a Stable Diffusion model, I generate images to add a new food class to the dataset (meatballs, of course) and I retrain the model with Python and the Hugging Face Transformers library. Finally, I deploy the model with Hugging Face Inference Endpoints. And of course, I answer questions!

In this new Hugging Face webcast, we discuss HuggingChat, our new open source chatbot, as well as the renewed partnership with AWS. We also show you how to accelerate Transformer training with AWS Trainium, and inference with AWS Inferentia2. And of course, we answer as any questions as possible!

AWS Inferentia2 is now generally available, and I couldn’t resist testing it with BERT models and comparing results with Inferentia1. This thing is FAST and looks very cost-effective. Check it out!

Real-life generative AI! In this video, I show you how to fine-tune a Google FLAN-T5 model to summarize legal text. We first deploy the model straight from the Hugging Face hub to Amazon SageMaker, and we evaluate it on legal data. Then, using GPU instances managed by SageMaker, we fine-tune the model with a Hugging Face script and we deploy it again.

More speed! In this video, you will learn how to accelerate image generation with an Intel Sapphire Rapids server. Using Stable Diffusion models, the Hugging Face Diffusers library, the Intel Extension for PyTorch and system-level optimizations, we’re going to cut inference latency from 36+ seconds to 5 seconds!

In this video, you will learn how to accelerate image generation with an Intel Sapphire Rapids server. Using Stable Diffusion models, the Hugging Face Optimum Intel library and Intel OpenVINO, we’re going to cut inference latency from 36+ seconds to 4.5 seconds!