Accelerating and Streamlining LLM AI Deployments
summary
Joint NetApp and F5 work aims to keep data in place and run LLM training and inference against it without mass migration, using integrations like BlueXP Workload Factory to augment models on Amazon Bedrock and connectors to Google BigQuery and Azure OneLake. The stack pairs NetApp storage with F5 networking (Big‑IP, load balancing) to feed massive GPU clusters, supports RAG workflows, and targets secure, compliant multicloud deployments at production scale.
AI-written summary · about
chapters (4)
related talks
33mAccelerating the LLM Lifecycle on the Cloud
09mAI, DPUs, and Distributed Workloads: What F5 and Nutanix Are Building Together
10mApproach to AI at a large scale
28mNavigating LLM deployment: Tips, tricks, and techniques
28mAnyscale's Unified Platform for LLM Development and Deployment
05mAI discussions and deployments in the UK
08mKeynote: Plug in and Scale: Serving LLM Models on Kubernetes Ma...
20mSecure, private LLMs in your cloud with Anyscale Endpoints