Showing 2026Show all
2 papers · 1 filter
cs.AR2026
HBM Is Not All You Need: Efficient Disaggregated LLM Serving across Memory-heterogeneous Accelerators
Zhixiang Wei, Yun Wang, James Yen +2
LLM inference comprises a compute-bound prefill phase and a memory-bound decode phase, and recent systems disaggregate them onto separate hardware. Yet today's datacenter GPUs rely…
cs.RO2026
Jiao: Bridging Isolation and Customization in Mixed Criticality Robotics
James Yen, Zhibai Huang, Zhixiang Wei +5
Consumer robotics demands consolidation of safety-critical control, perception pipelines, and user applications on shared multicore platforms. While static partitioning hypervisors…