Excited to announce our judges for this Sunday's agents and compound AI hackathon with LangChain and Factory! Join us to push the boundaries of agents and compound AI and to chat with folks like Matan Grinberg, Sunny Rochiramani, Dmytro Dzhulgakov , swyx.sg, Harrison Chase, Roland, David Vendrow

Moved inference over to Fireworks AI because the API is more reliable. Getting about 162 toks on concurrent requests with llama 3.1 8B model, plus this allows for 100k+ context. Structured generation is also supported which makes the citation verification approach more

Come join us Poe hackathon this Saturday 8/17, with cohosts: Poe Adam D'Angelo Fireworks AI Modal ! Each admitted participant will receive a $500 credit from Modal and $30 credit from Fireworks AI ! Both online and In-person participation options

Introducing the 2024 Next #BillionDollarStartups Artificial intelligence dominates this year’s list of 25 venture-backed startups we think most likely to reach a $1 billion valuation. Read more: trib.al/uE8F50y

The north star for Fireworks AI is simple API access to the totality of knowledge. The big unlock? Compound AI systems orchestrating 10's/100's/1000's of models and components. On Episode 9 of Training Data from @Sequoia, Pat Grady and I spoke to Lin Qiao about compound AI.

Huge thank you to everyone who participated in our Agents and Compound AI Systems Hackathon this weekend with Fireworks AI and Factory! We had great talks from Harrison Chase and Eno Reyes, and saw impressive projects exploring new possibilities with agentic systems. See👇 for

For Lin Qiao and the Fireworks AI team, the mission is to accelerate training and inference with low-latency, cost-effective solutions. On the latest episode of Training Data from @Sequoia, Sonya Huang 🐥 and Pat Grady talked to Lin about democratizing access to GenAI, when

Thrilled to see Fireworks on the Forbes Next Billion-Dollar Startups list! No surprise that AI companies are leading the charge—AI is reshaping industries, and we're at the forefront. Proud of our unstoppable team, but we're just getting started. Join us and help shape the future

Yam Peleg OnDemand does this with their BYOM. Fireworks AI has On Demand Deployments. A great way to run Dolphin! 🐬 By the way, I am building the infrastructure to host Dolphin myself. In my garage. Will be up and running within the next month.

Cognitive Computations Yam Peleg OnDemand Fireworks AI love this video youtube.com/watch?v=kPXvf2…

👀Check out the latest RAG tutorial using Llama 3.1 using Astro, SurrealDB and FastAPI , where you can update the embeddings live and retrieve and add context via the Llama 3.1 405B model fireworks.ai/blog/rag-with-…

The world of AI is moving fast, but to build production-ready applications and deliver real value, developers need to focus on more than just models. Whether you’re building the next billion-dollar startup or getting started with generative AI, here’s how to stay ahead: 1️⃣ Build

🔥 Join Fireworks AI and Shape the Future of AI! At Fireworks AI, we’re building the fastest, most scalable AI infrastructure, backed by top investors like Benchmark and Sequoia. Our team of industry veterans from Meta's PyTorch, Google, and more, is on a mission to empower AI

Great advice for #startups from the co-founder Fireworks AI on moving fast and avoiding the "paralysis of analysis." Don't miss our conversation with one of the leading voices in AI innovation! Listen wherever you get your podcasts.🎧 #StartupSuccess burklandassociates.com/podcasts/scali…

Planning a trip? Check out this tutorial for a function-calling recommendation system to pull flight details from user inputs! fireworks.ai/blog/function-… Built with: ✅ Firefunction-v2 ✅ FastAPI as backend ✅ NextJS (Vercel ai sdk) as frontend ✅ SerpApi for real-time info

🔥 Introducing FireOptimizer 🔥 An adaptation engine to customize LLM serving for your unique use case. It optimizes LLM performance by adjusting hardware setup, model, and software layers of our inference stack, using techniques like adaptive speculative execution, adaptive

🔧 FireOptimizer from Fireworks AI offering up to 3x latency improvement - that will be great. 🎯 Achieves 76% hit rate vs 29% for generic models, 2x faster vs 1.5x slower The secret - FireOptimizer employs a new technique called adaptive speculative execution which

Hackathon alert! 🚨 The registrations for the Code Interpreting 2.0 are open! Make a team, build the best AI agent or app with E2B Code Interpreter SDK & Fireworks AI LLMs. Win cool prizes, and meet people like swyx. Thanks, Edge for providing the amazing venue.