# Balancing Coverage and Draft Latency in Vocabulary Trimming for Faster Speculative Decoding

arXiv: https://arxiv.org/abs/2603.05210 · HTML: https://mlsanity.com/paper/2603.05210/

## 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 14 of its 18 references that are in the map.
- First posted on arXiv 5 Mar 2026.

## Placed in

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

## Builds on (most cited first, 14 of 14)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (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)
- [Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding](https://mlsanity.com/paper/2401.07851/) (2024)
- [Advancing LLM Reasoning Generalists with Preference Trees](https://mlsanity.com/paper/2404.02078/) (2024)
- [Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performance](https://mlsanity.com/paper/2304.11127/) (2023)
- [The Perfect Blend: Redefining RLHF with Mixture of Judges](https://mlsanity.com/paper/2409.20370/) (2024)
- [VOCABTRIM: Vocabulary Pruning for Efficient Speculative Decoding in LLMs](https://mlsanity.com/paper/2506.22694/) (2025)
- [Training Domain Draft Models for Speculative Decoding: Best Practices and Insights](https://mlsanity.com/paper/2503.07807/) (2025)

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

- [SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding](https://mlsanity.com/paper/2605.10453/) (2026)

## Abstract (arXiv)

Speculative decoding accelerates inference for Large Language Models by using a lightweight draft model to propose candidate tokens that are verified in parallel by a larger target model. Prior work shows that the draft model often dominates speculative decoding latency, since it generates tokens sequentially and incurs high cost from its language modeling head as vocabulary size grows. This exposes a fundamental trade-off in draft model design: larger vocabularies improve token coverage and agreement with the target model, but incur higher draft latency, while smaller vocabularies reduce latency at the risk of missing tokens required for accurate draft generation. We address this trade-off through vocabulary trimming for draft models, motivated by the observation that domain-specific workloads use only a small fraction of the full vocabulary. We cast draft vocabulary selection as a constrained optimization problem that balances token coverage and draft latency. Coverage is computed over assistant responses in the training data, while latency is estimated using architecture-aware FLOPs that capture the cost of the language modeling head as a function of vocabulary size. We optimize a utility function with a Tree-structured Parzen Estimator to efficiently explore the coverage-latency Pareto frontier under a minimum coverage constraint. Experiments show improved speculative decoding throughput while reducing draft vocabularies by up to 97% with high coverage. On domain-specific tasks, we achieve up to 16% latency reduction and 20% throughput improvement, and up to 6.7% throughput gains on diverse out-of-distribution tasks.