🚀 World record performance: SambaNova is running Llama 3.1 405B at 114 t/s with full precision accuracy, in only one rack. Verified by Artificial Analysis! 🦙 This speed unlocks so many use cases for enterprises and developers that we cannot wait to see them built on our platform. Apply for early access today: sambanova.ai/fast-api See Llama 3.1 405B in action ⚡️ sambanova.ai Read our blog to learn more: https://lnkd.in/gcZi6cC6 #FastAI #LLM #GenerativeAI
SambaNova Systems
Computer Hardware Manufacturing
Palo Alto, CA 46,325 followers
Purpose built for pervasive AI
About us
AI is changing the world and at SambaNova, we believe that you don’t need unlimited resources to take advantage of the most advanced, valuable AI capabilities - capabilities that are helping organizations explore the universe, find cures for cancer, and giving companies access to insights that provide a competitive edge. We’ve built an enterprise-ready AI platform from the ground up - intentionally designed for the most valuable and complex AI workloads of today and tomorrow. Using our platform to build a technology backbone for the next decade of AI innovation, organizations get pre-trained Foundation Models that truly transform the way they gain value from AI and deep learning. And, with our flagship offering, Dataflow-as-a-Service™, we help them realize value 22x faster. SambaNova was founded in 2017 in Palo Alto, California, by a group of industry luminaries, business leaders, and world-class innovators who understand AI. Today, we’ve built an incredibly smart and motivated team dedicated to making a lasting impact on the industry and equipping our customers to thrive in the new era of AI.
- Website
-
http://www.sambanova.ai
External link for SambaNova Systems
- Industry
- Computer Hardware Manufacturing
- Company size
- 201-500 employees
- Headquarters
- Palo Alto, CA
- Type
- Privately Held
- Founded
- 2017
- Specialties
- High Performance Computing, Artificial Intelligence, Machine Learning, GPT3, Foundation Models, Deep Learning, Computer Vision, True Resolution, 3D Image Analysis, Recommendation, AI Platform, Large Language Models, AI for Science, and Generative AI
Locations
-
Primary
Bayshore Fwy
Palo Alto, CA 94303, US
Employees at SambaNova Systems
Updates
-
SambaNova Systems reposted this
This past week we onboarded our first wave of developers using our Llama 3.1 405B API service. Several thousand developers got to experience the world’s fastest and most accurate Llama3.1 405B - full 16 bit precision for highest accuracy at up to 125 tokens per second! Come to sambanova.ai and get your free developer credits and try it!
-
What if we told you that you can switch between AI models in milliseconds? ⚡️ With our unique RDU chip architecture, the SN40L, you can do so with ease. SambaNova Fast API also includes free rate-limited token credits, so you can get started right away. Learn more 👉 https://lnkd.in/g9W_Bnjv #FastAI #LLM #API
-
Large monolithic models are a thing of the past! With Sambaverse, developers can discover, compare, and evaluate open source models, addressing the most common challenges when it comes to training AI solutions. Check out the Sambaverse: https://lnkd.in/eQMb7Tvd #Developers #AIChips #LLM
This content isn’t available here
Access this content and more in the LinkedIn app
-
SambaNova is the platform for building Agentic AI. 🏆 For most of these use cases, developers will need a mixture of expert models, not just 405B, all running at the fastest inference speeds. ⚡️ With our API, developers can bring their own Llama fine tuned checkpoints to the platform to be utilized alongside 405B. The best part? Thanks to our RDU, all these models run on a single node. Sign up here for early access 👉 https://lnkd.in/g9W_Bnjv #MachineLearning #AI #MetaAI Anton McGonnell
-
-
This article from The Information reveals that DOJ investigators are looking at whether Nvidia pressured cloud providers to buy multiple Nvidia products. SambaNova CEO & Co-founder, Rodrigo Liang, is quoted in the piece: "Whenever you have someone approaching 90% market share in a highly competitive environment, the biggest thing that customers are concerned about is that their success is being decided by a [single] vendor, Nvidia." If you're subscribed to The Information, you can read the full article here 👇 https://lnkd.in/esgC-GMi #GenerativeAI #AI #AIChips
-
-
As we predicted, Llama 405B is starting to be used by developers to generate training data and fine tune expert models to solve business problems. SambaNova is the best platform to generate this data at 4X the speed. 🚀🚀🚀🚀 Want to get started? Developers can sign up for early access here 👇 https://lnkd.in/g9W_Bnjv #OpenSource #AI #MetaAI Anton McGonnell
-
-
Have you heard of a Composition of Experts model? A CoE, when run on a purpose-built architecture, solves the challenge of larger models’ high costs by enabling faster adoption of AI in the enterprise. These are some insights you’ll learn in this white paper: ✅ How to ensure your enterprise, not a model vendor, gets the benefits of Generative AI 🔒 How to protect your data with unrivaled data privacy 🚀 How to power the next generation of AI with industry-leading performance and accuracy Download now 👉 https://lnkd.in/gM_zqete #LLM #GenerativeAI #AIChips
-
-
Our predictions for Meta’s Llama 3.1 announcement are coming true! Every provider is racing for the most efficient API, including us. And our API is 4X faster than the median provider for serving Llama 405B 🏎️💨 Developers can get started by signing up for early access here👇 https://lnkd.in/g9W_Bnjv #MetaAI #AI #GenerativeAI Anton McGonnell
-
-
Open source quality has now caught up to proprietary models like GPT-4o with the release of Llama 3.1 405B 16-bit 🦙 Experience speeds that are 4X the median provider from just a single 16 chip rack. Try Llama 405B for yourself today at sambanova.ai ⚡️ #LLM #GenerativeAI #MachineLearning
-