2 papers
cs.DC2026
OACM: Optimistic Asynchronous Communication Model for Large-Scale SNN Simulation
Guangnan Feng, Yangle Zeng, Honghui Liang +2
Spiking Neural Network (SNN) simulation serves as a crucial tool for understanding brain dynamics and advancing neuromorphic computing, but faces significant scalability challenges…
cs.LG2026
Analytical Provisioning for Attention-FFN Disaggregated LLM Serving under Stochastic Workloads
Chendong Song, Meixuan Wang, Hang Zhou +5
Attentio-FFN disaggregation (AFD) is an emerging architecture for LLM decoding that separates state-heavy, KV-cache-dominated Attention computation from stateless, compute-intensiv…