← all papers · overview

Stepcache: Step-level Reuse With Lightweight Verification And Selective Patching For LLM Serving

Abstract

We address LLM serving workloads where repeated requests share a common solution structure but differ in localized constraints, such as output schema, variable names, or numeric constants. Prior caching approaches typically reuse either full responses (semantic caching) or model-internal KV/prefix states, which are respectively brittle under partial changes or tightly coupled to specific backends.

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).