2 papers
cs.AR2026
NOVA: Technology-Architecture Co-Design of Near-Memory Processing for Attention-SSM-MoE Hybrid LLM Inference
In-Jun Jung, Jaeha Min, Joo-Young Kim
The rapid evolution of hybrid large language models (LLMs), which interleave grouped-query-attention (GQA), state-space model (SSM), and Mixture-of-Experts (MoE) layers, introduces…
cs.AR2026
3DLS: A 3D Logic-Stacked Architecture for Disaggregated LLM Serving
Jaehun Lee, In-Jun Jung, Joo-Young Kim
Large language model (LLM) serving increasingly combines prefill-decode (PD) disaggregation with tensor parallelism (TP) to support large models and long contexts. In conventional…