Memory in the AI Era, Part 5: Exploring CXL Workloads
We examine how CXL is used in real workloads through KV cache offload, memory pooling, and memory tiering.
KV Cache
Transformer World: A Deep Dive into the Building Blocks of LLMs
A hands-on walkthrough of Transformer-based LLM internals — from each module’s role to key optimization techniques.
Know Your Enemy, Know Yourself, Part 4: Memory Capacity Bottleneck and NVIDIA ICMS
We explore the technical principles behind NVIDIA’s ICMS — a new storage tier designed to solve the KV cache capacity bottleneck in LLMs — and the Bluefield-4 DPU that manages it.