| Challenge: | Speculative decoding (SD) uses an efficient draft model to generate multiple tokens . previous methods depend on simple heuristics to select K or dynamically adjust the window size . |
| Approach: | They propose a framework that allows a draft model to generate multiple tokens . they propose HSDDW, which allows the draft model autonomously decide when to stop generating tokens. |
| Outcome: | The proposed framework outperforms existing state-of-the-art methods on four datasets. |
Similar Papers
EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Speculative decoding is a key technique for enhancing the inference speed of Large Language Models. |
| Approach: | They propose a method that adds padding tokens to ensure that the number of new tokens remains consistent across samples. |
| Outcome: | The proposed method can handle the issue of inconsistent prediction tokens without adding padding tokens. |
MARS: Unleashing the Power of Speculative Decoding via Margin-Aware Verification (2026.findings-acl)
Copied to clipboard
Jingwei Song, Xinyu Wang, Hanbin Wang, Xiaoxuan Lei, Tianyu Shi, Shixin Han, Eric Yang, Xiao-Wen Chang, Lynn Ai
| Challenge: | Autoregressive large language models suffer from high inference latency due to memorybandwidth constraints. |
| Approach: | They propose a method that decouples generation and verification by decoupling tokens and a lightweight draft model. |
| Outcome: | The proposed method delivers consistent and significant speedups over state-of-the-art baselines while preserving generation quality across diverse benchmarks. |
Speculative Verification: Exploiting Information Gain for Speculative Decoding (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are used for many applications but their size and computational cost make inference serving a significant challenge. |
| Approach: | They propose an efficient augmentation to Speculative Decoding (SD) that predicts speculation accuracy and dynamically adapts the verification length to maximize throughput. |
| Outcome: | The proposed model reduces wasted verification on rejected tokens and improves decoding efficiency. |
Multi-Drafter Speculative Decoding with Alignment Feedback (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to accelerate large language model (LLM) inference use a smaller model to draft future tokens, which are then verified by the target LLM. |
| Approach: | They propose a unified framework that integrates multiple drafters into the SD process. |
| Outcome: | Extensive experiments show that MetaSD outperforms single-drafter approaches. |
Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Conventional speculative decoding methods use a predefined length policy for proposing drafts, but the reality deviates from this assumption. |
| Approach: | They propose a self-verification length policy that adaptively determines the lengths of draft sequences by referring to the draft entropy. |
| Outcome: | The proposed method achieves 17% speedup on MT-Bench and 22% speedup in long-form reasoning. |
Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding (2025.findings-naacl)
Copied to clipboard
Sukmin Cho, Sangjin Choi, Taeho Hwang, Jeongyeon Seo, Soyeong Jeong, Huije Lee, Hoyun Song, Jong C. Park, Youngjin Kwon
| Challenge: | Existing methods for drafting and verifying tokens require significant fine-tuning or have inconsistent performance across tasks. |
| Approach: | They propose a lossless drafting approach that organizes various token sources into multiple databases in a hierarchical framework based on temporal locality. |
| Outcome: | The proposed method outperforms existing database drafting methods on Spec-Bench using 7B and 13B parameters. |
Graph-Structured Speculative Decoding (2024.findings-acl)
Copied to clipboard
Zhuocheng Gong, Jiahao Liu, Ziyue Wang, Pengfei Wu, Jingang Wang, Xunliang Cai, Dongyan Zhao, Rui Yan
| Challenge: | Speculative decoding is a promising technique to accelerate the inference of Large Language Models. |
| Approach: | They propose a method that uses a token graph to record multiple sequence hypotheses within a single draft stage. |
| Outcome: | The proposed method significantly accelerates the inference of Large Language Models (LLMs) it allows the LLM to choose from and select the longest sequence that meets its standards. |
Draft
& Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for accelerating Large Language Models have been criticized for their inference costs and inefficient decoding. |
| Approach: | They propose a self-speculative decoding approach for accelerating Large Language Models without an auxiliary model. |
| Outcome: | The proposed method achieves a speedup of up to 1.99 with no additional neural network training and no extra memory footprint. |
SpecHub: Provable Acceleration to Multi-Draft Speculative Decoding (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have limited inference speed due to sequential token generation . Spechub is a novel, efficient sampling-verification method for MDSD that improves acceptance rates with only linear computational overhead. |
| Approach: | They propose a method that uses a smaller draft model to generate multiple token sequences . Spechub generates 0.05-0.27 and 0.02-0.16 more tokens per step than RRS and RRS without replacement . |
| Outcome: | The proposed method improves acceptance rates with only linear computational overhead. |
HCSpec: Two-Tier Horizontal Cascade Speculative Decoding for High-Efficiency Large Language Model Inference (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to decode large language models adopt a homogeneous architecture . autoregressive decoding is a bottleneck because tokens must be generated sequentially . |
| Approach: | They propose a framework that organizes heterogeneous position-specialized draft modules into a horizontal cascade. |
| Outcome: | The proposed framework outperforms the current state-of-the-art (EAGLE3) and achieves 3.72x acceleration over vanilla decoding. |