At this year's @Supercomputing
, we’re highlighting our high-performance inference & fine-tuning. Paired with unparalleled power-efficiency & availability in cloud or on-premise, our unique architecture is the ultimate accelerator for powering the next wave of #AI.
@sambanovaai
-
High-Performance AI Inference and Fine-Tuning Architecture Unveiled
By
–
-
Open Source AI: Benefits and Challenges at Slush 2026
By
–
Our Chief Technologist & Co-Founder, @KunleOlukotun will be onstage at @SlushHQ on Nov. 20th. He’ll be speaking about the benefits & challenges of #opensource #AI alongside: @Thom_Wolf – @huggingface @graceisford – @Lux_Capital @ravmattu – @nytimes
-
Two NLP Papers Presented at EMNLP, One Wins Best Award
By
–
We will be at @emnlpmeeting presenting two papers, one of which has won The Best Paper Award at Custom4NLP Workshop! Check em out here SambaLingo: https://
bit.ly/3YROYAl Constructing Domain: https://
bit.ly/40PHcK6 #GenerativeAI #LLM #Inference -
SambaNova Lightning Fast AI Hackathon Extended to November
By
–
Great news, hackers! We've extended the Lightning Fast AI Hackathon deadline to Nov 22nd.
— SambaNova (@SambaNovaAI) 14 novembre 2024
This means more time to build on SambaNova Cloud. Remember, there's a $10k prize pool up for grabs! 🤑
Get hacking ➡️ https://t.co/FyJr51Mj1n pic.twitter.com/MGqC5xVpwmGreat news, hackers! We've extended the Lightning Fast AI Hackathon deadline to Nov 22nd. This means more time to build on SambaNova Cloud. Remember, there's a $10k prize pool up for grabs! Get hacking https://
sambanova.devpost.com -
SambaNova Cloud Launches Function Calling for AI Applications
By
–
We're excited to announce that function calling is now available on SambaNova Cloud! This powerful feature allows you to create more sophisticated & interactive #AI apps. Take your projects to the next level, & check out our documentation https://
bit.ly/48Su6gV -
SambaNova Llama 3.1 405B Breaks Speed Records at 200 Tokens Per Second
By
–
Just over here breaking speed records! 🚀
— SambaNova (@SambaNovaAI) 14 novembre 2024
Get ready to revolutionize your agentic apps with our Llama 3.1 405B models, now running up to 200 tokens per second! 🤯
Experience the fastest inference on the market: https://t.co/GgqtX90zsS pic.twitter.com/1sDLaMSgAPJust over here breaking speed records! Get ready to revolutionize your agentic apps with our Llama 3.1 405B models, now running up to 200 tokens per second! Experience the fastest inference on the market: https://
cloud.sambanova.ai -
SambaNova Cloud Llama 3.1 405B 200 tokens second
By
–
🚨The fastest is even faster on @AIatMeta's Llama 3.1 405B!
— SambaNova (@SambaNovaAI) 13 novembre 2024
SambaNova Cloud runs 200t/s! 🚀
Use it to:
✅ Leverage the best open source model while coding
✅ Build the next wave of #AIAgents
✅ Crush it at Hackathons
Try it for free ⤵️The fastest is even faster on @AIatMeta
's Llama 3.1 405B! SambaNova Cloud runs 200t/s! Use it to: Leverage the best open source model while coding Build the next wave of #AIAgents Crush it at Hackathons Try it for free -
SambaNova Cloud Platform Speeds Validated by AI Community
By
–
@ArtificialAnlys just put our speeds to the test and we're loving the results! Thank you, to the real MVP of #AI validation! Try it for yourself at https://
cloud.sambanova.ai @AIatMeta -
SambaNova Cloud Accelerates Llama 3.2 AI Inference Performance
By
–
Reach for the stars with SambaNova Cloud!
— SambaNova (@SambaNovaAI) 13 novembre 2024
Unlock fast #AI inference on @AIatMeta's Llama 3.2 1B & 3B with unmatched performance — all running at full precision.
Start building today ⤵️Reach for the stars with SambaNova Cloud! Unlock fast #AI inference on @AIatMeta
's Llama 3.2 1B & 3B with unmatched performance — all running at full precision. Start building today -
SambaNova Benchmarking Starter Kit for Production AI Apps
By
–
Our Benchmarking Starter Kit is here to help devs like you evaluate & test your apps in production, ensuring seamless integration with #SambaNova at max speed & latency. Learn more: