2 papers
cs.AR2026
AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving
Zhongkai Yu, Haotian Ye, Chenyang Zhou +9
All current LLM serving systems place the GPU at the center, from production-level attention-FFN disaggregation to NVIDIA's Rubin GPU-LPU heterogeneous platform. Even academic PIM/…
cs.DC2025
Utility-Driven Speculative Decoding for Mixture-of-Experts
Anish Saxena, Po-An Tsai, Hritvik Taneja +2
GPU memory bandwidth is the main bottleneck for low-latency Large Language Model (LLM) inference. Speculative decoding leverages idle GPU compute by using a lightweight drafter to…