BentoML

📢 macOS users! Do you know you can now run LLMs right on your macOS with OpenLLM? ✨ Try out some of the popular models with a simple command using `openllm serve`! openllm serve phi3:3.8b-ggml-q4 openllm serve llama3.2:1b-instruct-ggml-fp16-darwin openllm serve qwen2.5:14b-ggml-q4 😺 More exciting news: we're working on MLC model versions to deliver up to 3x faster inference on macOS — same models, lightning speed! ⚡ Check out the demo and stay tuned for more OpenLLM updates! #LLM #AI #macOS #OpenLLM #OpenSource

⚠️ 3 days left! The countdown is on for the #AGIBuildersMeetup in NYC! Get ready for an exciting evening of tech talks, community demos, and networking! Spaces are filling up fast and register today to secure your spot! 

If you’re working with AI for semantic search, recommendation engines, or information retrieval, you’re likely familiar with embedding models. Our latest blog dives into some of the top open-source embedding models, covering their strengths, use cases, and key points for deployment to consider. 👉 Check out the full article and start exploring the best model for your needs: https://lnkd.in/gackKSnz #AI #MachineLearning #OpenSource #Embeddings #BentoML

🚀 Welcome to the #AGIBuildersMeetup — and this month, we’re heading to NYC! We’re thrilled to co-host it with Yext and would like to invite all #AI builders, researchers, and enthusiasts for an exciting evening! We will have the latest AI insights from #Yext, #BentoML, and AI21 Labs, plus community demos from LaunchDarkly and Haize Labs! 🗓️ When: Wednesday, October 30th, 5:30 PM - 8:00 PM, EDT 📍 Where: New York City (Register to see the address) 🔗 Register now to secure your spot! Link: https://lu.ma/3h9jb07l #OpenSource #AI21Labs #LaunchDarkly #HaizeLabs

🌟 #AGIBuildersMeetup tour kickoff this Thursday! 🚀 4 events across 3 cities in 3 weeks 10/24 in SF Infra for AI Agents with OpenAI, Meta, Replit, E2B, Letta, and Latent Space 10/29 in ATL Scaling AI in Production with Tecton, Chick-fil-A Corporate Support Center-fil-A and BentoML 10/30 in NYC Builders night with Yext, AI21 Labs, LaunchDarkly, Haize Labs, and BentoML 11/07 in SF Builders night with Intercom, Fleak, Dify.AI, and BentoML 🎟 Limited seats, secure your spot today! 💕 Spread the love with likes, shares, and invites! 👇 Link in the comment.

Everyone talks about AI agents as the next big thing, but what infrastructure/tooling is required to put them to work? 🔥Join us this Thursday (10/24) in SF for an in-depth discussion on "Infra for AI Agents." 🌟 We have an incredible line-up of speakers: Researcher keynotes from: - Shunyu Yao, Research Scientist OpenAI - Shuyan Zhou, Researcher Meta, incoming asst. Professor Duke University Builder panel featuring: - James Austin, staff SWE @Replit AI (core team for Replit Agent) - Vasek Mlejnsky, co-founder & CEO E2B - Charles Packer, co-founder & CEO Letta and our friend Shawn swyx W, podcast host @Latent Space 💡 Come hear insights from top researchers, startup founders and AI agent/agent infra builders on the latest advancements and opportunities in AI agent tooling and infra. 🍕 Plus, enjoy refreshments and plenty of networking! Thanks BentoML Eventual for hosting this! 📅Spots are limited. Approval only. RSVP now and network with the brightest in AI! https://lu.ma/xv15gkkp #AI #AGI #AIInfrastructure #aiagents #SFMeetup #TechEvents #startups #SFevents

🤖️ Want to deploy an LLM agent that combines reasoning + real-time web search? In our latest blog post, we demo how to use #BentoML to deploy a #LangGraph #LLM agent that: ✅ Leverages an open-source LLM served via BentoML, providing OpenAI-compatible APIs ✅ Retrieves real-time information from the web with #DuckDuckGo if it lacks the necessary knowledge ✅ Handles long-running workloads asynchronously ✅ Runs on #BentoCloud’s optimized infrastructure 👉 Read the full tutorial here: https://lnkd.in/gUwYtjnm #OpenSource #AI #MachineLearning

Tomorrow is the day! Join us at 5:30 PM PDT for the MLOps Community Meetup on Democratizing AI Infra! Get ready for great conversations and insights into the latest in AI and MLOps. See you! 🎉