KV-cache compression

OrbitFlow

OrbitFlow: SLO-Aware Long-Context LLM Serving with Fine-Grained KV Cache Reconfiguration

On the frontierfirst seen Jan 5, 2026

Current frontier — recent, not yet superseded in the knowledge base

0 papers critique it · 0 beat it on benchmarks

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.