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.
intro You might have heard of the “recursive .gitignore symptom”, or maybe you havenโtโbut if you work with Git long enough, thereโs a good chance youโll run into it. Itโs one of those sneaky issues that can cause unexpected behavior in your repositories, making files disappear from Git tracking when you least expect it. Imagine …
Read more “Recursive `.๐๐๐ก๐๐๐๐๐๐`: When Ignoring Goes Too Far”
Intro This is part three of our Vault for Dummies series. After Part 2 where we set up Vault with Transit Auto-unseal, itโs time to tackle Kubernetes authentication, from outside the cluster. In this post, weโll walk through setting up Kubernetes auth with an external Vault, so your K8s workloads can securely authenticate and pull …
Read more “HashiCorp Vault for Dummies: K8s Auth setup in an External Vault (WSL)”