Cerebras Inference not only sent Groq Inc a shot across the bow, it nuked their viral Feb results from orbit. Cerebras is now the cheapest, and fastest, Llama 3 provider in the world, by a huge margin, AND at full precision. Bonus: they matched Gemini Flash's 1m tok/day free

Hello, Dream of a Website That You Want on Infinity Internet: Such as "Cheesecake Heaven", or "Counter-Strike 2 Bunny Hopping Guide" - Anything! Live Demo: infinityinternet.singularityon.com #OpenSource #AI #InfinityInternet True Open Source Download the #PHP: github.com/alby13/infinit…

Added support for Cerebras to thefastest.ai, and their Llama 3.1 70B implementation is now our best performer in US West (and neck and neck with Groq Inc in US East). Exciting to see the robust competition here!

i still have api keys to give away - DM me with the open source projects you want to build 👷🏗️

llama 3.1 8b on cerebras

this video is not sped up - it actually generates full html pages in less than a second Cerebras llama3.1-8b is crazy fast it's not the smartest, but imagine when something as smart as Claude 3.5 Sonnet is this fast!

Kicking off Hands-on RAG night with Daniel Kim talking inference with Cerebras at Cloudflare SF

Was super fun running today’s Developer Workshop with Lizzie Siegle and Daniel Kim! Lizzie talked about Cloudflare Workers AI Daniel talked about insanely fast inference with Cerebras Weaviate tied it all together with RAG with vectors from CF and Inference from Cerebras!

How many AI engineers does it take to screw in a lightbulb? Idk but some combo of Cloudflare Weaviate • vector database and Cerebras can probably find the answer for you in a jiffy 🏃‍♂️💨

Finally getting to play around with Cerebras WOW this is fast. Ran some benchmarks with AgentOps 🖇️-- LLM calls are 5-10x faster than OpenAI (llama 3.1-70b vs gpt-3.5-turbo)

Trelis Assistant (assistant .Trelis.com) just got upgraded to ultra-fast Llama-3.1-70B with Cerebras . - Upload your docs - Get answers with verified citations ~1-2 second turnaround Give it a tinker, there are free credits when you log in.

Join us tomorrow, Sept 12th at Zoom HQ in San Jose for our second developer meetup! Here is the speaker lineup and their topics: ⭐ Pooja Mistry 🌸 , Postman : Revolutionizing API Testing and Development with AI ⭐ David Gu , recall.ai : Building an interactive AI agent

Zoom’s AI developer meetup is returning! Join us on Sept 12th at Zoom HQ in San Jose lu.ma/jjgnoqik Speakers: ⭐️Pooja Mistry 🌸: Postman ⭐David Gu: recall.ai ⭐ojusave: Zoom, Jason Koo: Neo4j ⭐️Daniel Kim: Cerebras ⭐️Frank Liu: Zilliz

With Cerebras' Llama3.1-8B now at 1927 tokens/s (up from 1800) and Llama3.1-70B reaching 481 tokens/s (up from 450), it's clear that not all Llama3.1 models are created equal—we remain the most accurate and fastest inference provider in the world! 🥇 🚀 To ensure the

psyched for two demos that I have prepared for our meetup today! 1. Creating a GraphQL endpoint with data from Zoom rest APIs and webhooks using Neo4j with Jason Koo 2. An in meeting assistant that answers questions if you don’t know the answer , this one uses Deepgram for

Daniel Kim in the house 🔥🔥🔥🔥🔥🔥 #zoomdevelopers

new swag drop 🍜 Cerebras