Intro Every once in a while, a new cloud platform shows up that doesnโt just offer โmore computeโ . It rethinks what the cloud should look like in an AI-first world. Thatโs what caught my attention with Nebius, a European-born cloud designed from the ground up for high-performance, AI-centric workloads. One that just closed a …
Intro Deploying vLLM manually is fine for a lab, but running it in production means dealing with Kubernetes, autoscaling, GPU orchestration, and observability. Thatโs where the vLLM Production Stack comes in – a Terraform-based blueprint that delivers production-ready LLM serving with enterprise-grade foundations. In this post, we’ll deploy it on Amazon EKS, covering everything from …
Read more “vLLM Production Stack on Amazon EKS with Terraform๐ง๐ผโ๐”
Intro We often hear about RAG (Retrieval-Augmented Generation) and vector databases that store embeddings, but we fail to remember what exactly are embeddings used for and how they work. In this post, weโll break down how embeddings work – in the simplest way possible (yes, like youโre 5 ๐ง ๐). I. What is an Embedding? Embeddings …
Intro If youโve played with vLLM locally you already know how fast it can crank out tokens. But the minute you try to serve real traffic with multiple models, thousands of chats, you hit the same pain points the community kept reporting: โ ๏ธ Pain point What you really want High GPU bill Smarter routing + …
Read more “vLLM production-stack: LLM inference for Enterprises (part1)”
Our Founder & CEO, Kosseila Hd, recently sat down with SafetyDetectives to share CloudThrillโs vision on why the real AI revolution lies in infrastructure rather than just apps, and what that means for organizations building and owning their private, scalable AI.