Recently we have been working extensively with AI in the lab. This has had wide-ranging results, from accidentally borking an entire OS with various configurations and software to needing to set up and have a baseline image to work with across platforms. We decided that it would be worth outlining the basic getting started steps as

New block and file services highlighted the HPE GreenLake Storage Day. While HPE emphasizes the operational and management benefits of making these services available in GreenLake, we’re interested in the new universal hardware platform that sits behind the scenes – the HPE Alletra MP storage server.

In recent months, large language models have been the subject of extensive research and development, with state-of-the-art models like GPT-4, Meta LLaMa, and Alpaca pushing the boundaries of natural language processing and the hardware required to run them. Running inference on these models can be computationally challenging, requiring powerful hardware to deliver real-time results.

Pi represents the ratio of a circle’s circumference to its diameter, and it has an infinite number of decimal digits that never repeat or end. Calculating infinite Pi isn’t just a thrilling quest for mathematicians; it’s also a way to put computing power and storage capacity through the ultimate endurance test. Up to now, Google’s

The Dell PowerEdge R660 is a 1U rackmount server designed to support the latest and greatest in server technology, including E3.S Gen5 storage, DDR5 memory, and configurations with liquid CPU cooling. It features support for two processors (dual sockets), 32 RDIMMs, and up to three graphics cards.

As the digital landscape has continued to evolve, storage solutions that can accommodate a wide range of enterprise workloads and emerging application development platforms have become increasingly important. Notably, Dell Technologies PowerStore is a primary storage array designed to meet the needs of both traditional enterprise workloads and modern, containerized applications running on Kubernetes (K8s).

The Supermicro SYS-111E-WR server offers an impressive range of features that make it a great option for organizations that need a compact high-performance computing solution. Supporting Intel’s 4th Gen Xeon Scalable Processors (single Socket LGA 4677) and PCIe Gen5 expansion, the SuperServer SYS-111E-WR is capable of handling a variety of workloads ranging from content delivery

It’s no secret that deploying an NVMe IP SAN can significantly improve workload performance, but the manual discovery and configuration overhead can be overwhelming and time-consuming. Traditional direct discovery methods require explicit knowledge of all hosts, subsystem NVMe Qualified Names (NQNs), and interface IP addresses. This is not much of a concern in smaller networks.

We reviewed the HP t640 thin client a few years ago and found the performance and build quality impressive. It was published just before the pandemic and the massive work-from-home (WFH) revolution, which, in effect, really pushed what we expect from a remote work device. Thin clients have come a long way in the past