Intro When scaling AI models like DeepSeek or Qwen on Amazon EKS, engineering teams obsess over GPU utilization while quietly bleeding money on storage bloat. Because standard EBS volumes force a 1:1 replica-to-disk ratio, scaling a single 70GB model to 20 pods doesn’t cost 70GB, it forces you to provision 1.4 Terabytes of redundant EBS …
Read more “vLLM on EKS: Cut LLM Storage Costs by 95% with S3 Mountpoint”
Intro The vLLM Production Stack is designed to run on any Kubernetes-based infrastructure. After covering AWS , Azure, Google Cloud and Nebius MK8s implementations, today we’re deploying vLLM production-stack on CoreWeave Kubernetes (CKS) with the same Terraform framework. CoreWeave is one of the hottest NeoCould built on the idea that GenAI workloads donโt need virtualization; they need direct access to …
Read more “vLLM Production Stack on CoreWeave CKS with Terraform๐ง๐ผโ๐”
Intro Every generation from an LLM is shaped by parameters under the hood. Knowing how to tune is important so that you can produce sharp and more controlled outputs. Here are the 7 levers that matter most. Make sure to try the interactive playground at the bottom to visualize and play with each parameter. 1) …
Intro Today, most of us have used nano banana, Midjourney, Kling AI, Luma, or Sora to generate silly videos or catchy images on socials. But what do they share in common? They all rely on Diffusion Models as their core engine, even the brand new Seedance. While many of these are proprietary, the open-source world …
Read more “Diffusion Models explained: From Noise to Pixels”
Intro A few weeks ago I wrote about why Intel Optane Persistent Memory was the ideal technology for LLM KV-cache offloading with a near-DRAM latency, and natively non-volatile. In other words, it behaved like memory but survived reboots. I also explained why CXL wasn’t quite the performance equivalent, due to higher latency and non persistence. But recently …