Storage and Networking Considerations for AI Deployments
Grand Mesa F
Wed Apr 29 | 8:15pm
Abstract
This Birds of a Feather session brings together some of our afternoon SMEs to discuss perspectives on AI‑optimized storage, from accelerated object storage for AI/ML to flash‑centric architectures for large‑scale LLM inference to KV‑cache offload designs powered by RDMA. This is your opportunity to get big questions answered.
