SNIA's library of recent presentations, videos, tutorials, white papers, and more are now accessible through our Educational Library. Archived content will continue to be added over the coming months.
| Pub Date | Title | Content Type |
|---|---|---|
| Storage for AI 103, An Introduction to Storage for Inference | Conference Session | |
| Data Storage Innovations for Scalable AI Infrastructure | Conference Session | |
| From Heuristics to Principles: A Practical Model for LLM Inference | Conference Session | |
| Scaling Inference with KV Cache Storage Offload and RDMA Accelerated Architecture | Conference Session | |
| AiSIO: Orchestrating Storage I/O Across CPUs and Accelerators | Conference Session | |
| Demystifying Data Flows through Typical LLM Training | Conference Session | |
| An Update on Accelerated Object Storage for AI/ML | Conference Session | |
| Scaling beyond memory: fine-grained GPU access to unbounded data for vector databases and graph neural networks | Conference Session | |
| Enabling AI Storage Benchmark Evolution at the Pace of AI | Conference Session | |
| AI Storage Workloads: What is Different and Impacts on SSD Design | Conference Session |
