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

arXiv:2609.38386 · cs.AI · Submitted 2026-09-29 · Read on arXiv

cs.AI

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/ggml-org/llama.cpp

Terminology

• Decode — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes

Sources

• Fairness-Aware and Latency-Controllable Scheduling for Chunked-Prefill LLM Serving
• Qwen3 Technical Report
• Deadline-Aware Adaptive Prefill Chunking for Efficient Large Language Model Serving

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems