🚀 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 47,083 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
-
Thank you for the shoutout, Andrew Ng! We have Llama 3.1 405B running at 120 tokens/sec at full precision on a really small footprint. We're so glad to see you having fun with our Fast API. 🔑 Want an API key? Reach out to us or sign up here 👉 https://lnkd.in/g9W_Bnjv #MetaAI #API #AI
I've been playing with SambaNova Systems's API serving fast Llama 3.1 405B tokens. Really cool to see leading model running at speed. Congrats to Samba Nova for hitting a 114 tokens/sec speed record (and also thanks Kunle Olukotun for getting me an API key!) https://lnkd.in/gQF-PmnK
-
Did you know that as a fully configured platform, SambaNova Suite offers the latest in best-in-class open source models? Our platform also includes Samba-1, the only 1T parameter Composition of Experts model. Learn more about SambaNova Suite👇 https://lnkd.in/gtzvZTcP #GenerativeAI #AI #FastAI
-
-
We always champion the democratization of AI. Because generative AI has the potential to be more transformative than the internet, we believe that everyone should have access to it. 📚 Established as a result of The White House Executive Order on the Safe, Secure and Trustworthy Development and Use of AI, the National Artificial Intelligence Research Resource (NAIRR) Pilot program aims to connect academics, research teams, and universities to computational, data, and training resources needed to advance AI research. SambaNova is proud to be a part of this effort! Learn more in our blog ⤵️ https://lnkd.in/gDeZXADa #GenerativeAI #NAIRR #AI
-
-
Our predictions about Meta’s Llama 3.1 405B are spot on 🔮 In the race for the fastest API, we’re proud to be leading the pack at 4X the speed of the median provider 🏎️💨 Ready to experience the speed? Sign up for early access now👇 https://lnkd.in/g9W_Bnjv #MetaAI #AI #GenerativeAI Anton McGonnell
-
-
Our AI chip is easily able to perform both training and inference on a single platform, eliminating the redundancy of legacy systems and to power the largest, multi-trillion parameter models that are enabling enterprise-grade generative AI. #AIChips #LLMs #Developers
This content isn’t available here
Access this content and more in the LinkedIn app
-
We set a world record! 🚀 SambaNova's Fast API is leading the race for performance and accuracy with Llama 3.1 405B, the largest and most capable open source AI model. At 4X the speed of other providers, you can be sure to get the most efficient API. Sign up for early access now 👉 https://lnkd.in/g9W_Bnjv Try Llama 3.1 405B for yourself at sambanova.ai⚡️ #MetaAI #FastAI #AI Anton McGonnell
-
-
Last week, Amol Sharma, SambaNova Principal Engineer, ML, attended The <AI / ALL> Summit in Bangkok along with other top minds in AI. He shared how a Composition of Experts model like ours can benefit your enterprise by allowing small, open source experts to beat large proprietary models. Thank you to SCB 10X for co-hosting a wonderful event! 🎉 #AI #MachineLearning #Developers
-
-
Not 1, not 2, not 3, but 4X the speed of other Llama 3.1 405B providers! Our API is winning the race for efficiency. 🏎️💨 Gain early access here ⤵️ https://lnkd.in/g9W_Bnjv Experience the world record speed at sambanova.ai ⚡️ #AI #MachineLearning #MetaAI Anton McGonnell
-
-
At SambaNova, our goal is to ensure that the powers of Generative AI aren't limited to just the top companies. Our CEO & Co-Founder Rodrigo Liang shares with Intel Capital’s Stephanie Cope, and Intel Corporation’s Camille Morhardt on InTechnology how we're democratizing AI by making it possible to run models with fewer chips. #AI #GenAI #LLM
ICYMI: SambaNova Systems is democratizing access to generative AI 👀 CEO Rodrigo Liang explains by making it possible to run models with fewer chips, SambaNova simplifies the generative AI deployment process while also improving model performance. Learn more from Rodrigo, Intel Capital’s Stephanie Cope, and Intel Corporation’s Camille Morhardt on InTechnology: https://bit.ly/3SWiVgm #generativeAI #InTechnology #AIchips