Scheduling LLM Inference with Uncertainty-Aware Output Length Predictions

arXiv:2604.00499 · cs.LG · Submitted 2026-04-01 · Read on arXiv

cs.LG

Submitted: 2026-04-01

Updated: 2026-05-25

Code: https://github.com/Hyzheng-code/TIE

Terminology

• Ablation — 7× in this paper · explained in 1 episode
• Generalization — 7× in this paper · explained in 13 episodes
• Robustness — 6× in this paper · explained in 5 episodes
• Consistency — 5× in this paper · explained in 3 episodes
• Synthetic Data Generation — 5× in this paper · explained in 5 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Embeddings — 4× in this paper · explained in 2 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Clustering — 3× in this paper · explained in 2 episodes
• Conditional Value-at-Risk — 3× in this paper
• Core — 3× in this paper · explained in 2 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• KV cache — 3× in this paper · explained in 3 episodes
• Quality of Service — 3× in this paper
• Tail Inflated Expectation — 3× in this paper
• Ablation Studies — 2× in this paper · explained in 1 episode
• Ablation study — 2× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• Few-Shot Learning — 2× in this paper · explained in 4 episodes
• Generalizability — 2× in this paper · explained in 6 episodes
• Online Adaptation — 2× in this paper · explained in 3 episodes
• Adaptive Strategy — 1× in this paper · explained in 1 episode
• Coefficient of Variation — 1× in this paper
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Graceful Degradation — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Metacognition — 1× in this paper · explained in 5 episodes
• Mixture-of-Experts (MoE) — 1× in this paper · explained in 7 episodes
• Mixture-of-Experts (MoE) Models — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Shortest Expected Processing Time — 1× in this paper
• Speculative Shortest-Job-First — 1× in this paper
• Thinking mode — 1× in this paper · explained in 2 episodes

Sources

• Adaptively Robust LLM Inference Optimization under Prediction Uncertainty
• Qwen3 Technical Report
• Fast Distributed Inference Serving for Large Language Models
• gpt-oss-120b & gpt-oss-20b Model Card
• Qwen2.5-1M Technical Report

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks