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 …
Intro Any-to-any multimodal models combining text, images, video, and audio are advancing AI, but their complex architectures, mixing autoregressive LLMs and diffusion transformers, make efficient serving very difficult. Current systems like OpenAI’s ChatGPT (text) and Sora (video) run as separate engines, lacking unified any-to-any pipelines. vLLM-Omni solves just that with a fully disaggregated serving system …
Intro In the previous post, we explored how the vLLM Production-Stack upgrades vanilla vLLM engine to an enterprise-grade platform. This time, weโll crack open the Helm chart, decoding the key knobs in values.yaml and showing deployment recipes that span from a minimal install to full cloud setups. Acknowledgment: While authored independently, this series benefited from …
Read more “vLLM production-stack: Deployment in the cloud (part2)”
Intro No invite? No quota? No problem. If youโve tried to create an account on CoreWeave, you already know the drill: thereโs No open self-registration, No free tier, and No โSign up with GitHubโโwithout an invite. That’s why I decided to write my first CoreWeave blog post. This post shows how to get started with …
Intro The vLLM Production Stack is designed to work across any cloud provider with Kubernetes. After covering AWS EKS, Azure AKS, and Google Cloud GKE implementations, today we’re deploying vLLM production-stack on Nebius Managed Kubernetes (MK8s) with the same Terraform approach. Nebius AI Cloud is purpose-built for AI/ML workloads, offering cutting-edge GPU options from NVIDIA …
Read more “vLLM Production Stack on Nebius K8s with Terraform๐ง๐ผโ๐”