2 papers
cs.DC2026
CrossPool: Efficient Multi-LLM Serving for Cold MoE Models through KV-Cache and Weight Disaggregation
Zhuoren Ye, Tianyu Wo, Dinghao Xue +4
Emerging LLM services increasingly host many sparse MoE models, yet most models receive sparse requests and remain cold. This creates a GPU memory problem: model weights are stable…
cs.DB2025
Rethinking Analytical Processing in the GPU Era
Bobbi Yogatama, Yifei Yang, Kevin Kristensen +9
The era of GPU-powered data analytics has arrived. In this paper, we argue that recent advances in hardware (e.g., larger GPU memory, faster interconnect and IO, and declining cost…