S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation

Documenti analoghi

• SQuat: Subspace-orthogonal KV Cache Quantization
  di: Wang, Hao, et al.
  Pubblicazione: (2025)
• Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding
  di: Wang, Pei-Shuo, et al.
  Pubblicazione: (2025)
• Few-Step Diffusion Language Models via Trajectory Self-Distillation
  di: Zhang, Tunyu, et al.
  Pubblicazione: (2026)
• Self Speculative Decoding for Diffusion Large Language Models
  di: Gao, Yifeng, et al.
  Pubblicazione: (2025)
• Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting
  di: Liu, Fangcheng, et al.
  Pubblicazione: (2024)