# Decode-Latency Feedback Prefill: A Model-Free Controller and Its Generalization Limits

> 全文为英语

**Published:** 2026年10月1日
**Author:** Gaurav Agarwal, Ashish Garg, Isha Singhal
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/articles/decode-latency-feedback-prefill-a-model-free-controller-and-its-generali

Concurrent autoregressive inference creates a fundamental interference problem: prefilling a newly arrived long prompt can delay tokens for requests that are already decoding. Fixed prefill chunks reduce this interference, but the best chunk size depends on the model, hardware,…

> 内容来自原始来源： **arXiv — cs.AI**
> [在 arXiv — cs.AI 阅读全文](https://arxiv.org/abs/2609.38386)

**标签：** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*