5 papers
NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement
Sookyung Choi, Seungyong Lee, Kangkyu Park +11
The paper introduces NELSSA, a system that combines GPUs with processing‑near‑memory (PNM) accelerators to efficiently serve large language model requests of varying context length…
StreamDQ: Near-Memory Weight DeQuantization in Custom HBM for Scalable AI Inference Acceleration
Minki Jeong, Daegun Yoon, Soohong Ahn +7
As large language models (LLMs) scale, their memory and computation demands have grown substantially, making weight-only quantization a widely adopted technique for reducing model…
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…
HPU: High-Bandwidth Processing Unit for Scalable, Cost-effective LLM Inference via GPU Co-processing
Myunghyun Rhee, Joonseop Sim, Taeyoung Ahn +6
The attention layer, a core component of Transformer-based LLMs, brings out inefficiencies in current GPU systems due to its low operational intensity and the substantial memory re…
MoSKA: Mixture of Shared KV Attention for Efficient Long-Sequence LLM Inference
Myunghyun Rhee, Sookyung Choi, Euiseok Kim +3
The escalating context length in Large Language Models (LLMs) creates a severe performance bottleneck around the Key-Value (KV) cache, whose memory-bound nature leads to significan…