SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference

arXiv:2606.31145 · cs.CL · Submitted 2026-06-30 · Read on arXiv

cs.CL

Submitted: 2026-06-30

Updated: 2026-11-04

Code: https://github.com/gkamradt/LLMTest_NeedleInAHaystack

Terminology

Sources

Related papers