Deploying new infrastructure requires some pre-work to make sure that the hardware you selected will meet your performance requirements. In this post I guide you on how to make the right choices when sizing FSx for ONTAP appropriately to provide optimal performance for your workloads. ... View more

KV (key-value) caching is a technique that is used to optimize LLM inference by storing previously calculated values in a KV cache so that these values don't need to be calculated again for every new token that is generated, which would otherwise be necessary. As model context windows grow ever larger, and inference platforms are utilized by more and more users, the size of the KV cache can quickly outpace the amount of available GPU memory. In certain scenarios, offloading KV cache entries to an external target can greatly increase inference server performance. ... View more

The new SSD capacity decrease capability of FSx for ONTAP Gen-2 file systems, transforms high-performance storage workloads management on AWS, offering true elasticity, cost control, and operational simplicity. In this post, I’ll detail how the SSD capacity decrease works, its benefits, and best practices for its implementation. ... View more

Interested in how NetApp utilizes UX Research?  Want to know how your feedback helps?  Explore the latest UX Research blog where we review a case study on UX benchmarking. Discover how NetApp uses UX benchmarks to transform user experiences by leveraging user feedback and data-driven insights.  ... View more

This blog post covers ONTAP storage options available on VCF 9, provides guidance on availability, data protection and recovery scenarios for both VM and Kubernetes workloads. ... View more