arXiv Computation and Language

TSS: Target-Side Sparsification for Speculative Decoding in Domain-Specific Large Language Models

The paper introduces TSS, a target-side sparsification framework that selectively skips layers in a target verifier during speculative decoding for domain-specific large language models. By exploring multi-layer skip configurations with an acceptance- and metric-aware breadth search, TSS reduces verification cost, increases draft acceptance, and can even improve downstream task performance without retraining. Experiments on Spec-Bench demonstrate consistent gains across domains and model scales, notably boosting translation throughput by 1.68× and improving BLEU scores significantly.

arXiv Machine Learning
Oct 7

APEX: Speculate smarter, not deeper

The paper introduces APEX, a learned controller that improves speculative decoding for large language models by dynamically selecting the best speculation strategy and adjusting draft depth during generation. APEX uses request‑level routing among EAGLE‑3, n‑gram, and draft‑model speculation, and block‑level depth adaptation based on causal decoding signals and verifier feedback. Integrated into vLLM and tested with Qwen3‑8B, APEX achieves up to 5.24× speedup over autoregressive decoding while reducing wasted tokens by 41% compared to fixed‑depth n‑gram speculation.

By Manvi Jha, Zach Zhang, Zhichao Xu, Linbo Liu, Sai Muralidhar Jayanthi, Vinayak Arannil
arXiv AI
Oct 27

T2D: Target-to-Draft Model Pruning & Adaptation for Efficient Speculative Decoding

The paper introduces T2D, a framework that prunes and adapts a target large language model into a draft model optimized for both inference latency and alignment with the target model’s outputs. By formulating draft model design as an optimization problem, T2D achieves up to 92% pruning while maintaining high speculative decoding performance across multiple target model families and domains. The resulting draft models can also be integrated with other speculative decoding techniques to yield additional gains.

By Shahriar Kabir Nahin, Xiao Ye, Muhao Chen, Ben Zhou, Anshuman Chhabra
arXiv AI
Jul 7

DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation

arXiv:2607. 05147v1 Announce Type: new Abstract: Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification.

By Xin Cheng, Xingkai Yu, Chenze Shao, Jiashi Li, Yunfan Xiong, Yi Qian, Jiaqi Zhu, Shirong Ma, Xiaokang Zhang, Jiasheng Ye, Qinyu Chen, Chengqi Deng, Jiping Yu, Damai Dai, Zhengyan Zhang, Yixuan Wei, Yixuan Tan, Wenkai Yang, Runxin Xu, Yu Wu, Zhean Xu, Xuanyu Wang, Muyang Chen, Rui Tian, Xiao Bi, Zhewen Hao, Shaoyuan Chen, Huanqi Cao, Wentao Zhang, Anyi Xu, Huishuai Zhang, Dongyan Zhao, Wenfeng Liang
arXiv Machine Learning
Sep 17

ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference

ASPIRE introduces a non‑synchronized batched self‑speculative decoding framework for long‑context LLM inference, addressing the memory bottleneck of attention by drafting tokens with sparse attention and verifying them with full attention. It combines a unified mixed forward pass, a lightweight online speculation scheduler that lets each request independently decide when to verify, and an intra‑draft refresh layer that updates the sparse context at every draft step. Experiments on three models and five benchmarks show 1.70–4.58× speedup over autoregressive baselines and a 27% average improvement over the strongest prior self‑speculative methods.

By Amir Ziashahabi, Hossein Entezari Zarch, Lei Gao, Murali Annavaram, Salman Avestimehr
Hugging Face Trending Papers
Jul 27

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference

Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory. We target latency-critical single-user settings where routed experts are staged on demand from CPU memory to a GPU or from Flash to a mobile NPU.