MCP has become the standard for connecting LLMs with tools and data – but it comes at a cost. In this article, we explore Agentic Skills as a lightweight, context-efficient alternative and show how both technologies complement each other. ... View more

🚀This article explores how Workload Factory removes friction for EDA IT and engineering teams by automating and simplifying storage configuration, accelerating DevTest-environments’ setup, and ultimately boosting time to market.🚀 ... View more

NetApp announces general availability of the Google Cloud NetApp Volumes Model Context Protocol (MCP) Server, enabling customers to manage Google Cloud NetApp Volumes using natural language through AI assistants such as Gemini CLI and other MCP‑compatible clients. With this release, developers and storage administrators can provision, configure, and operate enterprise storage resources directly from AI‑powered interfaces, reducing operational complexity and accelerating day‑to‑day workflows. ... View more

In this post, we explore the merits of ONTAP pNFS for KV cache offloading. Based on our testing, using ONTAP pNFS over RDMA for your shared KV cache tier yields up to a 99% improvement in time to first token (TTFT) when compared to vanilla vLLM with no KV cache offloading, and up to an 86% improvement in TTFT when compared to a vLLM+LMCache setup that only utilizes the CPU memory (system RAM) for offload.   ... View more

Google Cluster Toolkit (open source, gcluster) helps you deploy repeatable EDA, AI/ML and HPC environments on Google Cloud—compute, networking, storage, and schedulers—using composable modules and blueprints. This blog discusses two approaches to provide NetApp Volumes backed shares storage to your Cluster Toolkit based compute cluster. ... View more