Looks like Molmo is not very good at GeoGuessr but I love the confidence

🛒 #BentoCloud is now available on #AWS Marketplace! We're thrilled to empower AWS customers with a complete platform to build and scale #CompoundAI systems! BentoCloud takes the infrastructure complexity out of production #AI workloads. It enables enterprise AI teams to run

2030: Geoffrey Hinton is receiving Nobel Peace Prize for his contribution to AI safety and preventing AI Apocalypse

🚀 We are excited to announce the #AGIBuildersMeetup is in NYC this month (lu.ma/3h9jb07l) and we will co-host it with Yext! We will have tech leaders from #Yext, #BentoML, and AI21 Labs to explore the latest AI topics! Also, expect insightful community demos from

📢 #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

At #AGIBuildersMeetup Intercom and BentoML - Infrastructure for Building AI Systems

I don’t need an AI to book flights and hotel for me. But this..

BentoML makes deploying ColPali a breeze! 😌 With features like adaptive batching and zero-copy I/O, it minimizes overhead even for large tensor data—perfect for fast and efficient deployments. Don’t miss the quickstart example repo I’ve created!

You can’t spell cocktail without AI..

Do you know you can take your #ComfyUI experience to the next level with #CustomNodes? Read our new blog post (bentoml.com/blog/a-guide-t…) to see the most popular ones - from advanced image enhancement to workflow optimization tools. Plus, find answers to FAQs: ✅ Why custom nodes

Structured decoding marks a fundamental shift in how we view and utilize LLM outputs. It is a crucial step towards building complex, agentic systems. In this joint blog post (bentoml.com/blog/structure…), we dive into structured decoding in vLLM. Key highlights: 🔧 vLLM now

Learn how to build, test, deploy, and monitor machine learning models in the cloud with the BentoML ecosystem. s.mtrbio.com/eqqjdilutz

🚀 Mistral AI just dropped Mistral Small 3.1! Key highlights: 📚 128k token context window 🤖 Improved text performance & multimodal understanding 💻 Runs on a Mac with just 32GB RAM ⚡ Outperforms Gemma 3 & GPT-4o Mini 🛠 Low-latency function calling 🔓 Fully open-source

Learn how #Yext cut time-to-market & compute costs by re-platforming #AI Inference on #BentoML: Key wins: ✅ 𝟯× 𝗳𝗮𝘀𝘁𝗲𝗿 model delivery (70 % less dev time) ✅ 𝗨𝗽 𝘁𝗼 𝟴𝟬 % 𝗚𝗣𝗨 𝘀𝗮𝘃𝗶𝗻𝗴𝘀 with cloud‑agnostic autoscaling ✅ 𝟮× 𝗺𝗼𝗿𝗲 𝗺𝗼𝗱𝗲𝗹𝘀 𝘀𝗵𝗶𝗽𝗽𝗲𝗱

#BentoFriday 🍱 — 20x Faster Iteration with BentoML Codespaces Modern #AI apps like #RAG or voice agents often require multiple powerful GPUs and complex dependencies. This often leads to: ❌ Painstaking delays with each code change ❌ Challenging environment setups ❌