作者位次 #4/14MICRO 2026Oral· PIM & Near-Memory Long-Context LLM Serving
NELSSA: A GPU–PNM Heterogeneous System for Mixed-Length LLM Serving via Length–based Request Placement
Sookyung Choi · Seungyong Lee · Kangkyu Park · Yunseo Chun · Junseok Lee · Hyeongseok Gwak · Myunghyun Rhee · Euiseok Kim · Donguk Moon · Kwangsik Shin · Guseul Heo · Youngpyo Joo · Hoshik Kim · Jongse Park