arXiv Machine Learning August 4, 2026 By Li Wang, Yi Su, Xiabao Wu, Chiran You, Yongchao Liu, Zhan Qiu, Juelu Zhang, Jiajun Zheng, Fangxin Liu, Jie Zhang, Chen Tian, Chengying Huan

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models

Read the original on arXiv Machine Learning →

arXiv:2608. 01651v1 Announce Type: cross Abstract: Hybrid-attention large language models combine full attention with recurrent linear attention to reduce long-context inference costs, yet their autoregressive decoding remains memory-bound.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 16

Nightjar: Dynamic Adaptive Speculative Decoding for Large Language Models Serving

arXiv:2512. 22420v5 Announce Type: replace-cross Abstract: Speculative decoding (SD) accelerates LLM inference by verifying draft tokens in parallel.

By Rui Li, Zhaoning Zhang, Libo Zhang, Huaimin Wang, Xiang Fu, Zhiquan Lai

llms efficiency benchmarks

arXiv Machine Learning

Jun 2

Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention

arXiv:2602. 07223v2 Announce Type: replace Abstract: Long-context large language model (LLM) inference has become the norm for today's AI applications.

By Yikang Yue, Yuqi Xue, Jian Huang

llms efficiency benchmarks

arXiv AI

Jul 1

SMART: When is it Actually Worth Expanding a Speculative Tree?

arXiv:2604. 09731v2 Announce Type: replace-cross Abstract: Tree-based speculative decoding accelerates autoregressive generation by verifying a branching tree of draft tokens in a single target-model forward pass.

By Lifu Wang, Pan Zhou

llms benchmarks

arXiv AI

Jul 24

SonicSampler: Unified Tile-Aware Kernels for LLM Sampling and Speculative Verification

arXiv:2607. 20475v1 Announce Type: new Abstract: Sampling in LLM inference comprises a combinatorial set of logit processing, token selection, and verification operations for speculative decoding.

By Pragaash Ponnusamy, Shivam Sahni, Jue Wang, Tri Dao

llms benchmarks safety

arXiv Machine Learning

Jun 3

Multi-Segment Attention: Enabling Efficient KV-Cache Management for Faster Large Language Model Serving

arXiv:2606. 02964v1 Announce Type: cross Abstract: Large Language Model (LLM) inference relies on key-value (KV) caches to avoid redundant attention computation.

By Chunan Shi, Yilei Chen, Yilin Chen, Xupeng Miao, Bin Cui

llms rag agents efficiency

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

llms efficiency benchmarks

Related stories

Nightjar: Dynamic Adaptive Speculative Decoding for Large Language Models Serving

Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention

SMART: When is it Actually Worth Expanding a Speculative Tree?

SonicSampler: Unified Tile-Aware Kernels for LLM Sampling and Speculative Verification

Multi-Segment Attention: Enabling Efficient KV-Cache Management for Faster Large Language Model Serving

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