RFC R-State — Resumable State Transfer Format for Heterogeneous LLM Pipeline Architectures
Pavel Scurin · Zenodo (CERN European Organization for Nuclear Research) · 2026
R-State is a proposed serialization format for transferring the internal state of large language models between stages of a heterogeneous inference pipeline without detokenization and re-tokenization. It is designed to reduce latency, preserve intermediate activations and KV-cache, and enable more modular multi-model workflows through a structured packet containing metadata and tensor payloads