1+ hour, 37+ min ago  (61+ words) ...

6+ day, 1+ hour ago  (285+ words) With VMware Data Services Manager (DSM), we are putting an end to the guesswork. By providing deep, granular visibility into database internals and unifying that data within the broader VMware Cloud Foundation (VCF) operations layer, we're giving practitioners the tools…...

2+ week, 1+ day ago  (650+ words) In a previous VMware Tanzu Data Intelligence update, we focused on foundational unification, bringing together data at rest and data in motion to support next-gen applications. We introduced vector capabilities for AI use cases and streamlined the integration between operational…...

2+ mon, 4+ day ago  (651+ words) This is part two of six in a multi-blog series providing a practitioner's guide to VMware Private AI Foundation with NVIDIA. The decision to host LLMs within a local Harbor registry offers significant strategic advantages for enterprises, particularly those dealing…...

3+ mon, 11+ hour ago  (126+ words) Todd is a performance engineer in the VMware Cloud Foundation (VCF) division at Broadcom who works with databases, servers, and storage. He is the co-creator and maintainer of the DVD Store open-source benchmark. The Extreme Performance Series is back for…...

3+ mon, 2+ week ago  (163+ words) To aid other enterprises who may be on a similar path, we are publishing a comprehensive methodology for turning open-source LLMs into invaluable domain experts. This guide outlines our approach using Llama 3. 1-8 B and VMware Cloud Infrastructure documentation, starting with…...

7+ mon, 2+ week ago  (332+ words) This blog post summarizes our white paper, "Deploy Distributed LLM inference with GPUDirect RDMA over Infiniband in VMware Private AI", which provides architectural guidance, detailed deployment steps, and technical best practices for distributed LLM inference across multiple GPU nodes on…...

10+ mon, 1+ week ago  (653+ words) We can assign more than one v GPU profile to one VM. One example of this is assigning multiple full GPUs (using full v GPU profiles) to the VM " most often used for handling large language models (LLMs) that do not…...