# OUTLETS: Output-Length Prediction from Speculative Decoding Backbones

arXiv: https://arxiv.org/abs/2609.01068 · HTML: https://mlsanity.com/paper/2609.01068/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Speculative decoding, one of 12 directions in Efficient LLM inference and serving.
- Builds on 27 of its 41 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Placed in

- Efficient LLM inference and serving / [Speculative decoding](https://mlsanity.com/inference/speculative-decoding/)

## Builds on (most cited first, 27 of 27)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees](https://mlsanity.com/paper/2406.16858/) (2024)
- [EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test](https://mlsanity.com/paper/2503.01840/) (2025)
- [Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free](https://mlsanity.com/paper/2505.06708/) (2025)
- [Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation](https://mlsanity.com/paper/2203.16487/) (2022)
- [Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding](https://mlsanity.com/paper/2402.05109/) (2024)
- [Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline](https://mlsanity.com/paper/2305.13144/) (2023)
- [Efficient LLM Scheduling by Learning to Rank](https://mlsanity.com/paper/2408.15792/) (2024)
- [SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths](https://mlsanity.com/paper/2405.19715/) (2024)
- [Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction](https://mlsanity.com/paper/2404.08509/) (2024)
- [Scheduling with Predictions and the Price of Misprediction](https://mlsanity.com/paper/1902.00732/) (2019)
- [Don't Stop Me Now: Embedding Based Scheduling for LLMs](https://mlsanity.com/paper/2410.01035/) (2024)
- [Overclocking LLM Reasoning: Monitoring and Controlling Thinking Path Lengths in LLMs](https://mlsanity.com/paper/2506.07240/) (2025)
- [SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding](https://mlsanity.com/paper/2603.18567/) (2026)
- [Predicting LLM Output Length via Entropy-Guided Representations](https://mlsanity.com/paper/2602.11812/) (2026)
- [Scheduling LLM Inference with Uncertainty-Aware Output Length Predictions](https://mlsanity.com/paper/2604.00499/) (2026)
- [Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios](https://mlsanity.com/paper/2511.20340/) (2025)
- [Robust Length Prediction: A Perspective from Heavy-Tailed Prompt-Conditioned Distributions](https://mlsanity.com/paper/2604.07931/) (2026)

## Built on by (most cited first, 1 of 1)

- [Jumping the Line: Exploiting Length Predictions in LLM Scheduling](https://mlsanity.com/paper/2610.03430/) (2026)

## Abstract (arXiv)

The heavy-tailed distribution of output lengths in Large Language Model (LLM) serving poses major challenges for resource provisioning and cluster scheduling. Although output-length prediction can mitigate these issues, existing approaches have key drawbacks: external proxy models add substantial latency and often have limited fidelity, whereas internal state-based methods are efficient but rely on shallow probes of current model states. We identify a structural connection between speculative decoding (SD) and length prediction: latent representations produced by the draft decoder in advanced frameworks (e.g., EAGLE-3) encode signals that are predictive of generation length. Building on this insight, we introduce OUTLETS (Output-Length Prediction from Speculative Decoding Backbones), which repurposes the speculative backbone as a trajectory-aware length predictor. When its draft representations are already computed for speculative decoding, OUTLETS adds only a lightweight regression head and achieves lower MAE than the evaluated methods. Under saturated disaggregated serving, OUTLETS predictions enable standard scheduling policies to prioritize shorter requests and distribute requests more evenly across decoding instances, reducing short-request P99 latency by 34.8%.