4 papers
Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding
Jianuo Huang, Yaojie Zhang, Qituan Zhang +3
Speculative decoding accelerates LLM inference by drafting multiple tokens and verifying them in parallel with the target model. However, its practical speedup is constrained by th…
FlexDraft: Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration
Yaojie Zhang, Jianuo Huang, Junlong Ke +5
Speculative decoding accelerates memory-bound LLM inference without quality degradation by using a fast drafter to propose multiple candidate tokens and the target model to verify…
Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference
Jianuo Huang, Yaojie Zhang, Yicun Yang +4
Diffusion large language models (dLLMs) present a promising alternative to dominant autoregressive models (ARMs) by the ability of parallel decoding at the expense of substantial c…
DebFlow: Automating Agent Creation via Agent Debate
Jinwei Su, Yinghui Xia, Yiqun Duan +4
Large language models (LLMs) have demonstrated strong potential and impressive performance in automating the generation and optimization of workflows. However, existing approaches…