# SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding

arXiv: https://arxiv.org/abs/2605.10453 · HTML: https://mlsanity.com/paper/2605.10453/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Speculative decoding, one of 12 directions in Efficient LLM inference and serving.
- Builds on 29 of its 33 references that are in the map.
- First posted on arXiv 11 May 2026.

## Placed in

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

## Builds on (most cited first, 29 of 29)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [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)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [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)
- [Break the Sequential Dependency of LLM Inference Using Lookahead Decoding](https://mlsanity.com/paper/2402.02057/) (2024)
- [Adaptive Input Representations for Neural Language Modeling](https://mlsanity.com/paper/1809.10853/) (2018)
- [REST: Retrieval-Based Speculative Decoding](https://mlsanity.com/paper/2311.08252/) (2023)
- [Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding](https://mlsanity.com/paper/2402.05109/) (2024)
- [Efficient softmax approximation for GPUs](https://mlsanity.com/paper/1609.04309/) (2016)
- [Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Models](https://mlsanity.com/paper/2506.11116/) (2025)
- [GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking](https://mlsanity.com/paper/1806.06950/) (2018)
- [FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling](https://mlsanity.com/paper/2502.14856/) (2025)
- [LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding](https://mlsanity.com/paper/2602.23881/) (2026)
- [VOCABTRIM: Vocabulary Pruning for Efficient Speculative Decoding in LLMs](https://mlsanity.com/paper/2506.22694/) (2025)
- [Deep Learning Meets Projective Clustering](https://mlsanity.com/paper/2010.04290/) (2020)
- [CORAL: Learning Consistent Representations across Multi-step Training with Lighter Speculative Drafter](https://mlsanity.com/paper/2502.16880/) (2025)
- [Speculative Decoding with a Speculative Vocabulary](https://mlsanity.com/paper/2602.13836/) (2026)
- [DynaSpec: Context-aware Dynamic Speculative Sampling for Large-Vocabulary Language Models](https://mlsanity.com/paper/2510.13847/) (2025)
- [Out-of-Vocabulary Sampling Boosts Speculative Decoding](https://mlsanity.com/paper/2506.03206/) (2025)
- [Balancing Coverage and Draft Latency in Vocabulary Trimming for Faster Speculative Decoding](https://mlsanity.com/paper/2603.05210/) (2026)

## Abstract (arXiv)

Speculative decoding speeds up autoregressive generation in Large Language Models (LLMs) through a two-step procedure, where a lightweight draft model proposes tokens which the target model then verifies in a single forward pass. Although the drafter network is small in modern architectures, its LM-head still performs projection to a large vocabulary, becoming one of the major computational bottlenecks. In prior work this issue has been predominantly addressed via static or dynamic vocabulary truncation. Yet mitigating the bottleneck, these methods bring in extra complexity, such as special vocabulary curation, sophisticated inference-time logic or modifications of the training setup. In this paper, we propose SlimSpec, a low-rank parameterization of the drafter's LM-head that compresses the inner representation rather than the output, preserving full vocabulary support. We evaluate our method with EAGLE-3 drafter across three target models and diverse benchmarks in both latency- and throughput-bound inference regimes. SlimSpec achieves 4-5× acceleration over the standard LM-head architecture while maintaining a competitive acceptance length, surpassing existing methods by up to 8-9% of the end-to-end speedup. Our method requires minimal adjustments of training and inference pipelines. Combined with the aforementioned speedup improvements, it makes SlimSpec a strong alternative across wide variety of draft LM-head architectures.