DynaMo: Accelerating Language Model Inference with Dynamic Multi-Token Sampling

Documenti analoghi

• MoDeGPT: Modular Decomposition for Large Language Model Compression
  di: Lin, Chi-Heng, et al.
  Pubblicazione: (2024)
• FlexiGPT: Pruning and Extending Large Language Models with Low-Rank Weight Sharing
  di: Smith, James Seale, et al.
  Pubblicazione: (2025)
• DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control
  di: Cui, Zichen Jeff, et al.
  Pubblicazione: (2024)
• MossNet: Mixture of State-Space Experts is a Multi-Head Attention
  di: Tuli, Shikhar, et al.
  Pubblicazione: (2025)
• GraphMERT: Efficient and Scalable Distillation of Reliable Knowledge Graphs from Unstructured Data
  di: Belova, Margarita, et al.
  Pubblicazione: (2025)