Showing cs.OSShow all
2 papers · 1 filter
cs.OS2026
The Ingestion Tax: Adopting File-Backed Weights in Tensor Frameworks
Yuan Si, Yufeng Lin, Daming Li +1
Open-weight models can occupy a middle capacity regime: active weights fit in DRAM as cached file pages, but a second framework-owned copy does not fit or must be refilled as layer…
cs.OS2026
Who Should Own the Expert Cache? Kernel-Managed Tiering for Trillion-Parameter MoE Inference
Yuan Si, Yufeng Lin, Daming Li +1
Mixture-of-experts models whose expert pools exceed DRAM capacity require a weight-residency tier. Existing systems manage it in user space with expert-granular placement, frequenc…