2 citations · 4 across the 4 of their papers we have counts for
Showing cs.ARShow all
3 papers · 1 filter
cs.AR2026
FLINT: Efficiently Leveraging High Bandwidth Flash for Capacity-Scalable LLM Inference Acceleration
Geraldo F. Oliveira, Arash Tavakkol, Xiangyu Zhu +10
LLM inference is increasingly constrained by accelerator memory capacity rather than compute throughput. This constraint is especially acute in single-accelerator and small-node in…
cs.AR2024★ 2 cited
A Novel Extensible Simulation Framework for CXL-Enabled Systems
Yuda An, Shushu Yi, Bo Mao +8
Compute Express Link (CXL) serves as a rising industry standard, delivering high-speed cache-coherent links to a variety of devices, including host CPUs, computational accelerators…
cs.AR2024★ 1 cited
InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference
Xiurui Pan, Endian Li, Qiao Li +6
The widespread of Large Language Models (LLMs) marks a significant milestone in generative AI. Nevertheless, the increasing context length and batch size in offline LLM inference e…