EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Documenti analoghi

• EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees
  di: Li, Yuhui, et al.
  Pubblicazione: (2024)
• EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
  di: Li, Yuhui, et al.
  Pubblicazione: (2024)
• AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls
  di: Du, Yu, et al.
  Pubblicazione: (2024)
• Rethinking Generative Large Language Model Evaluation for Semantic Comprehension
  di: Wei, Fangyun, et al.
  Pubblicazione: (2024)
• Test-Time Learning for Large Language Models
  di: Hu, Jinwu, et al.
  Pubblicazione: (2025)