Luis Ancajas | Director, Disaggregated Memory Systems
Micron

Future of Memory and Storage - Day 1 @ 10:05

Accelerating HPC and AI Work-loads using Disaggregated Memory Systems

In this session Luis will present practical demonstrations and performance analysis of using CXL-based disaggregated memory to accelerate large-scale AI inferencing workloads in HPC and datacenter environments. The approach integrates a CXL JBOM (Just a Bunch of Memory) as an offload target for the KV cache, connecting it to NVIDIA’s Dynamo inference stack via Micron’s FAMFS, enabling the JBOM to operate as a warm memory file system. This architecture removes storage bottlenecks and significantly increases the effective memory bandwidth available to the KV cache. Preliminary results indicate a 5–10× speedup over traditional storage-backed KV cache implementations, highlighting the transformative impact of CXL memory pooling for next-generation inference systems. This work presents a scalable, standards-aligned approach for deploying memory-intensive inference pipelines in modern HPC systems and data centers.

Luis Ancajas, Director, Disaggregated Memory Systems, Micron

×

Luis Ancajas / Accelerating HPC and AI Work-loads using Disaggregated Memory Systems

Luis Ancajas, Director, Disaggregated Memory Systems,
Micron

Luis Ancajas is Director for Disaggregated Memory Systems, at Micron Technology, where he leads strategy and ecosystem partnerships for next‑generation memory solutions supporting AI and data‑center workloads. With a background in computer architecture and semiconductors, he focuses on advancing...

CloseMore