arXiv:2607. 19223v1 Announce Type: new Abstract: Speculative decoding, in which a lightweight draft model first generates a draft sequence that is then verified in parallel by the target model, has become a prevalent paradigm for accelerating large language model inference.
By Yu-Yang Qian, Hao-Cong Wu, Chen Chen, Jiacheng Sun, Zhenhua Dong, Peng Zhao, Zhi-Hua Zhou
Speculative decoding, in which a lightweight draft model first generates a draft sequence that is then verified in parallel by the target model, has become a prevalent paradigm for accelerating large language model inference. Recent work such as DFlash further boosts drafting efficiency by leveraging diffusion drafters, whose parallel denoising mechanism enables draft generation in a single forward pass.
arXiv:2606. 11552v1 Announce Type: cross Abstract: Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their autoregressive decoding process incurs substantial inference costs due to inherently sequential token generation.
By Lexington Whalen, Yuki Ito, Ryo Sakamoto
Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their autoregressive decoding process incurs substantial inference costs due to inherently sequential token generation. Speculative decoding addresses this bottleneck by employing a lightweight draft model to propose multiple future tokens that are subsequently verified in parallel by a larger target model.
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
The paper introduces DCOCO (DFlash Contextual Corrector), a lightweight mechanism that restores intra-block dependencies in speculative decoding by evaluating multiple candidate tokens for contextual compatibility across adjacent draft positions. DCOCO maintains parallel drafting while enabling contextually informed token selection at low additional cost. Across multiple verifier backbones and benchmarks, DCOCO achieves the highest average throughput, delivering speedups of up to 6.6× over vanilla decoding and outperforming competing methods by 6–23% under concurrent serving loads.
By Roy Eisenstadt, Harel Lidar, Tal Gonen, Omer Luxembourg, Itamar Zimerman, Lior Wolf, Eli David, Ilan Naiman