Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding

Documenti analoghi

• CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs
  di: Ning, Zhiyuan, et al.
  Pubblicazione: (2025)
• Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation
  di: So, Junhyuk, et al.
  Pubblicazione: (2025)
• SRT: Accelerating Reinforcement Learning via Speculative Rollout with Tree-Structured Cache
  di: Chang, Chi-Chih, et al.
  Pubblicazione: (2026)
• Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding
  di: Zhao, Yilong, et al.
  Pubblicazione: (2025)
• Spiffy: Multiplying Diffusion LLM Acceleration via Lossless Speculative Decoding
  di: Agrawal, Sudhanshu, et al.
  Pubblicazione: (2025)