10 papers
A CXL Memory Rack for Multi-Turn LLM Serving
Hakbeom Jang, Inho Song, Sam H. Noh +2
Long-context, multi-turn, and agentic LLM workloads increasingly reuse previously processed context, making KV-cache reuse essential for reducing redundant computation. However, th…
ITME: Inference Tiered Memory Expansion with Disaggregated CXL-Hybrid Memories
Hakbeom Jang, Younghoon Min, Sunwoong Kim +5
The rapid shift toward agentic and long-context workloads in Large Language Models (LLMs) is pushing the industry beyond the capacity of individual servers toward disaggregated sha…
Characterization of Multi-Model Agentic AI Systems on General Tasks via Trace-Driven Simulation
Donghwan Kim, Prakhar Singh, Younghoon Min +3
Agentic AI completes tasks through iterative planning, tool use, and reasoning based on observed outcomes. Despite its popularity, its system-level behavior remains poorly understo…
Hybrid Adaptive Tuning for Tiered Memory Systems
Xi Wang, Jie Liu, Shuangyan Yang +3
Memory tiering provides a cost-effective solution to increase memory capacity, utilization, and even bandwidth. Memory tiering relies on system software for memory profiling, detec…
Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs
Wentao Ni, Kangqi Zhang, Zhongming Yu +7
As long-context inference becomes central to large language models (LLMs), attention over growing key-value caches emerges as a dominant decoding bottleneck, motivating sparse atte…
TraCT: Disaggregated LLM Serving with CXL Shared Memory KV Cache at Rack-Scale
Dongha Yoon, Younghoon Min, Hoshik Kim +2
Disaggregated LLM serving improves resource efficiency by separating the compute-intensive prefill phase from the latency-critical decode phase. However, this architecture introduc…