Cover Image

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Penghui, Du, Cunxiao, Zhang, Fengzhuo, Wang, Haonan, Pang, Tianyu, Du, Chao, An, Bo
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation
by: Zhang, Xuan, et al.
Published: (2024)

BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms
by: Hou, Yunlong, et al.
Published: (2025)

Annealed Relaxation of Speculative Decoding for Faster Autoregressive Image Generation
by: Li, Xingyao, et al.
Published: (2026)

Demystifying the Slash Pattern in Attention: The Role of RoPE
by: Cheng, Yuan, et al.
Published: (2026)

When Attention Sink Emerges in Language Models: An Empirical View
by: Gu, Xiangming, et al.
Published: (2024)

ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts
by: Georganas, Evangelos, et al.
Published: (2025)

SpecHub: Provable Acceleration to Multi-Draft Speculative Decoding
by: Sun, Ryan, et al.
Published: (2024)

Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation
by: Zhang, Ziyin, et al.
Published: (2024)

SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding
by: Li, Shenggui, et al.
Published: (2026)

SpecExtend: A Drop-in Enhancement for Speculative Decoding of Long Sequences
by: Cha, Jungyoub, et al.
Published: (2025)

HiSpec: Hierarchical Speculative Decoding for LLMs
by: Kumar, Avinash, et al.
Published: (2025)

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning
by: Xu, Yuhang, et al.
Published: (2026)

Training Domain Draft Models for Speculative Decoding: Best Practices and Insights
by: Hong, Fenglu, et al.
Published: (2025)

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration
by: Wen, Zhuofan, et al.
Published: (2024)

DistillSpec: Improving Speculative Decoding via Knowledge Distillation
by: Zhou, Yongchao, et al.
Published: (2023)

Muon Outperforms Adam in Tail-End Associative Memory Learning
by: Wang, Shuche, et al.
Published: (2025)

POSS: Position Specialist Generates Better Draft for Speculative Decoding
by: Huang, Langlin, et al.
Published: (2025)

CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs
by: Ning, Zhiyuan, et al.
Published: (2025)

SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths
by: Huang, Kaixuan, et al.
Published: (2024)

Spiffy: Multiplying Diffusion LLM Acceleration via Lossless Speculative Decoding
by: Agrawal, Sudhanshu, et al.
Published: (2025)

Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies
by: Timor, Nadav, et al.
Published: (2025)

Traversal Verification for Speculative Tree Decoding
by: Weng, Yepeng, et al.
Published: (2025)

Balancing Coverage and Draft Latency in Vocabulary Trimming for Faster Speculative Decoding
by: Shoham, Ofir Ben
Published: (2026)

When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training
by: Wang, Haonan, et al.
Published: (2024)

Free Draft-and-Verification: Toward Lossless Parallel Decoding for Diffusion Large Language Models
by: Wu, Shutong, et al.
Published: (2025)

Optimizing Anytime Reasoning via Budget Relative Policy Optimization
by: Qi, Penghui, et al.
Published: (2025)

SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention
by: Zhu, Qianchao, et al.
Published: (2024)

Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMs
by: Goel, Raghavv, et al.
Published: (2024)

DynaSpec: Context-aware Dynamic Speculative Sampling for Large-Vocabulary Language Models
by: Zhang, Jinbin, et al.
Published: (2025)

EvoSpec: Evolving Speculative Decoding via Real-Time Vocabulary and Parameter Adaptation
by: Zhang, Shuyu, et al.
Published: (2026)

Adaptive Draft-Verification for Efficient Large Language Model Decoding
by: Liu, Xukun, et al.
Published: (2024)

Defeating the Training-Inference Mismatch via FP16
by: Qi, Penghui, et al.
Published: (2025)

MineDraft: A Framework for Batch Parallel Speculative Decoding
by: Tang, Zhenwei, et al.
Published: (2026)

ConfSpec: Efficient Step-Level Speculative Reasoning via Confidence-Gated Verification
by: Liu, Siran, et al.
Published: (2026)

SpecExit: Accelerating Large Reasoning Model via Speculative Exit
by: Yang, Rubing, et al.
Published: (2025)

OWL: Overcoming Window Length-Dependence in Speculative Decoding for Long-Context Inputs
by: Lee, Jaeseong, et al.
Published: (2025)

Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding
by: Shen, Yuhao, et al.
Published: (2026)

Make Every Draft Count: Hidden State based Speculative Decoding
by: Chen, Yuetao, et al.
Published: (2026)

SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration
by: Wen, Zhuofan, et al.
Published: (2026)

Understanding R1-Zero-Like Training: A Critical Perspective
by: Liu, Zichen, et al.
Published: (2025)