2 papers
cs.DC2026
Validating Hybrid-State Cache Recovery for GLM-5.3-Flash with vLLM and LMCache
Frank Li
External cache transfers can succeed while a hybrid language model resumes from an inconsistent state. We examine the full 45-layer GLM-5.3-Flash model, using the RedHatAI/ GLM-5.3…
cs.DC2026
Shared KV Caching for Replicated 27B Inference: Correctness Failures and Performance Boundaries
Frank Li
Shared host-memory caching can avoid repeated prefill when a request moves between inference replicas. Its usefulness depends on both correct state transfer and lost prefix localit…