Hands-on training webinars covering real-world operations with MinIO AIStor—from capacity expansion and natural language management to seamless data lake migration with Apache Iceberg.
Join this MinIO training webinar to learn how to leverage AI assistance in handling a common administrative operation - reclaiming storage from your versioned AIStor buckets. Discover how AI-assisted analysis can identify reclaimable space and help you move beyond blunt lifecycle rules or hand-written cleanup scripts with precise, prefix-level cleanup strategies.See how the “plan, confirm, act” pattern enables safe, repeatable operations through live demonstrations. Walk away with practical AI-augmented techniques to reduce storage costs, improve efficiency, and stay in control of your versioned data at scale.
Deploying MinIO MemKV for Inference Context Memory Performance
Presenter: Ravind Kumar, MinIO Curriculum Engineer and Phil Sweany, MinIO Curriculum Engineer
Join this MinIO training webinar to learn how MemKV eliminates the critical bottleneck in your high performance inference servers. As inference models scale to longer contexts and higher concurrency, the context memory becomes the physical limitation to maintaining high throughput with the fastest Time to First Token (TTFT) and consistently speedy Time Per Output Token (TPOT). When GPU memory fills up, prefill latency and context recompute dominates and throughput collapses. MemKV provides a distributed shared context memory store that bridges GPU memory and memory-mapped NVMe drives to massively increase context memory space and avoid active context eviction and recompute. See how MinIO MemKV implements zero-copy RDMA, native NIXL integration, parallelized extent-based block store, and shared-nothing linear scalability to deliver massively increased aggregate throughput with sub-millisecond latency using existing commodity hardware.
Architecting AIStor Table Sharing with Databricks for Scale and Performance
Presenter: Smarika Pathak, MinIO Curriculum Engineer and Will Dinyes, Head of Certification
Join this MinIO training webinar to learn how to leverage AI assistance in handling a common administrative operation - reclaiming storage from your versioned AIStor buckets. Discover how AI-assisted analysis can identify reclaimable space and help you move beyond blunt lifecycle rules or hand-written cleanup scripts with precise, prefix-level cleanup strategies. See how the “plan, confirm, act” pattern enables safe, repeatable operations through live demonstrations. Walk away with practical AI-augmented techniques to reduce storage costs, improve efficiency, and stay in control of your versioned data at scale.
.svg)
.svg)