Why Kubernetes Cannot Contain a Full Lazy-Pulling Cache: Two Impossibility Results and a Bounded, Honest Design for Model Serving
cs.DC, cs.OS, cs.PF
Submitted: 2026-11-09
Updated: 2026-11-17
Comments: 10 pages, 2 figures. Under review at IEEE Access. Data, protocols, and harness: https://github.com/kliukovkin/lazy-model-delivery-study
Code: https://github.com/kliukovkin/lazy-model-delivery-study
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
Related papers
- Programmable Probabilistic Computer with 1,000,000 p-bits
- BatchGen: An Architecture for Scalable and Efficient Batch Inference
- Seamless Reconfiguration for DAG-BFT (Technical Report)
- ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
- iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
- TIRx: A Unified Tile Primitive ML Compiler Across Heterogeneous Backends