ONTAP MCP Goes GA: Full-Stack AI for NAS, SAN & NVMe-oF
We’re thrilled to announce the General Availability (GA) of ONTAP MCP, a groundbreaking releas ...read more
Overview
The NetApp Cyber Resilience Suite delivers comprehensive recovery assurance against any disruption—whether caused by human error, infrastruct ...read more
Cloud storage is often approached as a foundational service that is easy to provision and simple to operate. Although this abstraction is intentional ...read more
A step-by-step playbook for taking application-consistent storage snapshots of an Oracle single-instance database — and recovering from them inside tight SLAs — using NetApp ONTAP Consistency Groups on Google Cloud NetApp Volumes (GCNV).
... View more
Learn more about using quick, inexpensive volume clones to speed developers with access to production data for enterprise applications, EDA work and more.
... View more
Say goodbye to the productivity drain of switching between your IDE and cloud consoles. The Google Cloud NetApp Volumes (GCNV) Cursor Agent integrates storage management directly into your coding environment. With over 430 developers already on board, this AI-powered tool simplifies storage tasks, provides intelligent insights, and enhances workflow efficiency—all within your IDE. Discover how this game-changing agent is transforming cloud storage management for developers.
... View more
Cloud storage shouldn't be a security trade-off. As an ONTAP user, you’ve relied on built-in ransomware intelligence to protect your most critical data. We've now brought that same proven technology to Google Cloud NetApp Volumes (GCNV), managed directly through the NetApp Console, a centralized platform that simplifies data management across hybrid and multi-cloud environments. This integration is allowing you to leverage NetApp Volumes advanced features.
... View more
In this post, we explore the merits of StorageGRID S3 for KV cache offloading. Based on our testing, using a StorageGRID S3 bucket 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 54% improvement in TTFT when compared to a vLLM+LMCache setup that only utilizes the CPU memory (system RAM) for offload.
... View more