Lightning fast inference is a critical aspect of LLMs and we deliver it. As we introduce the world to SambaNova Cloud, we're excited for devs to unlock the full potential of Llama 3.1 70B & 405B to enable advanced AI applications. Read more
@sambanovaai
-
Fast API Llama 405B: 4X Speed Single Rack Efficiency
By
–
We had to hop on the trend Some very demure, very mindful facts about our fast API: 4X the speed of other Llama 405B providers Runs on a single rack at less than 19kW Full precision with the highest accuracy Composition of Experts model to support customer
-
AI Leaders Breakfast: Future of Financial Services Discussion
By
–
Breakfast with a side of AI On September 17, @RodrigoLiang will join Alexander Ratner, @SnorkelAI CEO & Founder, for an executive breakfast along with some of the greatest minds in the industry to discuss the future of AI in financial services. #AI #FinServ #GenAI
-
Which Llama provider features matter most to developers
By
–
Dev community, we'd love your insight! We know there are lots of Llama providers out there, so we're curious: which of these features are the most important to you? #Devs #GenAI
-
Meta Llama 3.1 405B Sets Speed Efficiency Record
By
–
Thank you to @SiddharthJin97 for his thoughtful piece on our performance milestone! We're proud to be a leader in AI speed and efficiency, setting the world record with Meta’s Llama 3.1 405B model at 4X faster than other providers. Read his full article on @Analyticsindiam
-
AI Revolution Won’t Be Monopoly: Infrastructure Challenges
By
–
The AI revolution will not be a monopoly. Our CEO & Co-Founder, @RodrigoLiang
, shares his thoughts at @theinformation
's AI Summit: "Customers are saying, ‘Oh, to deploy [a large number of GPUs,] I also have to buy a power plant?’ Liang said. 'As users, maybe we don’t -
SambaNova Reduces AI Energy Consumption with Llama Meta
By
–
Just listened to this insightful episode of @BBCRadio4 The Artificial Human with @aleksk and @Kevin_Fong
, where they discuss the problem of high energy consumption in AI. https://
bbc.co.uk/sounds/play/m0
0208g4
… With our record breaking performance, SambaNova is proud to run Meta’s Llama -
SubgoalXL: AI Breakthrough in Automated Mathematical Theorem Proving
By
–
New blog alert Introducing SubgoalXL, a significant step forward in the field of AI-powered theorem proving. By combining novel methodologies with state-of-the-art hardware, we've demonstrated that AI can tackle increasingly complex mathematical reasoning tasks with
-
CEO shares Llama 405B record performance at Global AI Summit
By
–
Our team will be at @globalaisummit 2024 next week where our CEO & Co-Founder, @RodrigoLiang
, will share more about our world record performance on the best open source model, Llama 405B. See you at #GAIN2024! Learn more https://
globalaisummit.org/en/default.aspx #AI #LLM -
SubgoalXL: Advanced AI Reasoning and Proof Formalization Framework
By
–
Check out our work: GitHub: https://
github.com/zhaoxlpku/Subg
oalXL
… Datasets & Models: https://
huggingface.co/collections/xl
-zhao/subgoalxl-66c84b77e0eaf131c0cdac15
… Paper: https://
arxiv.org/abs/2408.11172
Join us in pushing the boundaries of AI reasoning! #AI #LLM #SubgoalXL #AIResearch #ProofFormalization #MachineAssistedProofs