HiSpec: Hierarchical Speculative Decoding for LLMs

• URL: http://arxiv.org/abs/2510.01336v1
• Date: Wed, 01 Oct 2025 18:04:14 GMT
• Title: HiSpec: Hierarchical Speculative Decoding for LLMs
• Authors: Avinash Kumar, Sujay Sanghavi, Poulami Das,
• Abstract summary: We propose a framework for speculative decoding that exploits $textitearly-exit (EE) models for low-overhead intermediate verification.<n>We show that HiSpec improves throughput by 1.28$times$ on average and by up to 2.01$times$ compared to the baseline single-layer speculation.
• Score: 15.347747465564458
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Speculative decoding accelerates LLM inference by using a smaller draft model to speculate tokens that a larger target model verifies. Verification is often the bottleneck (e.g. verification is $4\times$ slower than token generation when a 3B model speculates for a 70B target model), but most prior works focus only on accelerating drafting. $\textit{``Intermediate"}$ verification reduces verification time by discarding inaccurate draft tokens early, but existing methods incur substantial training overheads in incorporating the intermediate verifier, increase the memory footprint to orchestrate the intermediate verification step, and compromise accuracy by relying on approximate heuristics. We propose $\underline{\textit{Hi}}\textit{erarchical }\underline{\textit{Spec}}\textit{ulative Decoding (HiSpec)}$, a framework for high-throughput speculative decoding that exploits $\textit{early-exit (EE) models}$ for low-overhead intermediate verification. EE models allow tokens to exit early by skipping layer traversal and are explicitly trained so that hidden states at selected layers can be interpreted, making them uniquely suited for intermediate verification without drastically increasing compute and memory overheads. To improve resource-efficiency even further, we design a methodology that enables HiSpec to re-use key-value caches and hidden states between the draft, intermediate verifier, and target models. To maintain accuracy, HiSpec periodically validates the draft tokens accepted by the intermediate verifier against the target model. Our evaluations using various representative benchmarks and models show that HiSpec improves throughput by 1.28$\times$ on average and by up to 2.01$\times$ compared to the baseline single-layer speculation without compromising accuracy.

Related papers

• Multi-Token Prediction via Self-Distillation [73.81494481537636]
  We consider a new approach for converting a pretrained autoregressive language model from a slow single next token prediction model into a fast standalone multi-token prediction model.<n>On GSM8K, our method produces models that can decode more than $3times$ faster on average at $5%$ drop in accuracy relative to single token decoding performance.
  arXiv  Detail & Related papers  (2026-02-05T18:54:48Z)
• TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification [63.65902785448346]
  Speculative decoding offers significant speed-ups through its lightweight drafting and parallel verification mechanism.<n>We propose TriSpec, a novel ternary SD framework that introduces a lightweight proxy to significantly reduce computational cost.<n>Experiments on the Qwen3 and DeepSeek-R1-Distill-Qwen/LLaMA families show that TriSpec achieves up to 35% speedup over standard SD.
  arXiv  Detail & Related papers  (2026-01-30T17:04:18Z)
• DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding [66.40658898418316]
  We present DiffuSpec, a training-free drop-in framework that uses a pretrained diffusion language model (DLM) to produce multi-token drafts in a single forward pass.<n>Across benchmarks, DiffuSpec yields up to 3x wall-clock speedup, establishing diffusion-based drafting as a robust alternative to autoregressive drafters for speculative decoding.
  arXiv  Detail & Related papers  (2025-09-28T07:00:15Z)
• Pipeline Parallelism is All You Need for Optimized Early-Exit Based Self-Speculative Decoding [73.67253077506672]
  Large language models (LLMs) deliver impressive generation quality, but incur very high inference cost.<n>Early-exit based self-speculative decoding (EESD) has emerged to mitigate this cost.<n>We propose Pipeline-Parallel Self-Speculative Decoding (PPSD) that fully pipelines the draft and verification work.
  arXiv  Detail & Related papers  (2025-09-19T04:51:41Z)
• LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation [15.04977852652768]
  Speculative decoding (SD) is a promising technique for LLM inference acceleration.<n>LogitSpec is motivated by the observation that the logit of the last token can not only predict the next token, but also speculate the next next token.<n>LogitSpec can achieve up to 2.61 $times$ speedup and 3.28 mean accepted tokens per decoding step.
  arXiv  Detail & Related papers  (2025-07-02T08:08:30Z)
• $\texttt{SPECS}$: Faster Test-Time Scaling through Speculative Drafts [55.231201692232894]
  $textttSPECS$ is a latency-aware test-time scaling method inspired by speculative decoding.<n>Our results show that $textttSPECS$matches or surpasses beam search accuracy while reducing latency by up to $sim$19.1%.
  arXiv  Detail & Related papers  (2025-06-15T05:50:05Z)
• Think Before You Accept: Semantic Reflective Verification for Faster Speculative Decoding [48.52389201779425]
  Speculative decoding accelerates inference by generating multiple draft tokens using a lightweight model and verifying them in parallel.<n>Existing verification methods rely heavily on distributional consistency while overlooking semantic correctness.<n>We propose Reflective Verification, a training-free and semantics-aware approach that achieves a better trade-off between correctness and efficiency.
  arXiv  Detail & Related papers  (2025-05-24T10:26:27Z)
• AutoJudge: Judge Decoding Without Manual Annotation [13.451750613294054]
  AutoJudge is a method that accelerates large language model (LLM) inference with task-specific lossy speculative decoding.<n>Our approach relies on a semi-greedy search algorithm to test which of the mismatches between target and draft models should be corrected.
  arXiv  Detail & Related papers  (2025-04-28T17:59:28Z)
• DEL: Context-Aware Dynamic Exit Layer for Efficient Self-Speculative Decoding [7.204881999658682]
  We introduce DEL, a plug-and-play method that adaptively selects the exit layer and speculation length during inference.<n>Del achieves overall speedups of $2.16times$$sim$$2.62times$ over vanilla auto-regressive decoding.
  arXiv  Detail & Related papers  (2025-04-08T01:12:59Z)
• ParallelSpec: Parallel Drafter for Efficient Speculative Decoding [62.68430939686566]
  We present ParallelSpec, an alternative to auto-regressive drafting strategies in state-of-the-art speculative decoding approaches. In contrast to auto-regressive drafting in the speculative stage, we train a parallel drafter to serve as an efficient speculative model.
  arXiv  Detail & Related papers  (2024-10-08T01:05:08Z)
• PEARL: Parallel Speculative Decoding with Adaptive Draft Length [12.166703341906242]
  We propose a conceptually simple, flexible, and general framework to boost speculative decoding, namely Parallel spEculative decoding with Adaptive dRaft Length (PEARL)<n>PEARL proposes pre-verify to verify the first draft token in advance during the drafting phase, and post-verify to generate more draft tokens during the verification phase.<n> Experiments on various text generation benchmarks demonstrate the effectiveness of our PEARL, leading to a superior speed up performance up to 4.43$times$ and 1.50$times$, compared to auto-regressive decoding and vanilla speculative decoding, respectively.
  arXiv  Detail & Related papers  (2024-08-13T08:32:06Z)
• DistillSpec: Improving Speculative Decoding via Knowledge Distillation [70.61777015900272]
  Speculative decoding (SD) accelerates large language model inference by employing a faster draft model for generating multiple tokens. We propose DistillSpec that uses knowledge distillation to better align the draft model with the target model, before applying SD. We show that DistillSpec yields impressive 10 - 45% speedups over standard SD on a range of standard benchmarks.
  arXiv  Detail & Related papers  (2023-10-12T16:21:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.