Book
Open access
Aug 2026
Replacing NVMe Staging in LLM Inference with a High-Bandwidth CXL Memory Expander with an On-Device DMA Controller
This work evaluates a CXL memory expander equipped with an on-device DMA controller as a high-performance staging tier in GDS-style data paths, sustaining high bandwidth for fine-grained LLM inference workloads such as KV cache updates.
Veerasenareddy Burru, Pradeep Kumar Nalla, Alok Prasad
· Conference on Applications,... · 0 citations