By adding RAG support, SambaNova Suite continues to deliver the performance, accuracy, and flexibility to power the largest models.

SambaStudio now supports text embedding models. This new feature significantly boosts the information retrieval capabilities of the SambaNova Suite and enhances large language models (LLMs) with Retrieval Augmented Generation (RAG) capabilities. RAG improves base LLMs on various aspects including factuality, reduced hallucinations, and more by providing correct context to the LLM. This functionality brings benefits to our customers and elevates the efficacy of the model.

As part of their on-going mission, Los Alamos National Laboratory has a new focus on deploying generative AI LLMs. To achieve this goal as quickly as possible, they have chosen the SambaNova Suite as the platform to deploy LLMs.

SambaNova Systems CEO and Co-Founder Rodrigo Liang was featured on the Unicorn Builders Podcast, produced by Front Lines. Listen in to learn about Rodrigo’s background in tech, what makes a great CEO, and his views on a startup mentality.

In this rapidly evolving landscape of pervasive AI, the choice between building or buying an AI solution is a critical one. SambaNova’s full-stack approach is a compelling solution for businesses...

As we enter the era of pervasive AI, the accuracy demanded by enterprise tasks means that LLMs will need to have trillions of parameters. These models will be composed of hundreds of smaller models, all working together as a Composition of Experts model, which provides a high degree of modularity and extensibility. This will be the next generation of model architecture.

Using a Composition of Experts model, SambaNova customers can take advantage of the benefits of multi-trillion parameter models with the performance of much smaller models.

SambaNova enhanced the SambaNova Suite – the only purpose-built, full stack LLM platform – with its revolutionary fourth-generation chip, the SN40L. The SN40L has a revolutionary, dataflow design making it capable of both dense and sparse computation. Combined with a three tier-memory structure comprising on-chip memory, high-bandwidth memory, and high-capacity memory, the SN40L enables 5 trillion+ parameter models with 256k+ sequence length capability.

At SambaNova, we have been researching and developing methods to train long sequence size (SS) models on our platform. Training longer sequence models has become paramount to enabling a variety of business applications such as summarizing long form documents and answering questions.