Login / Signup

Accelerating Production LLMs with Combined Token/Embedding Speculators.

Davis WertheimerJoshua RosenkranzThomas P. ParnellSahil SunejaPavithra RanganathanRaghu K. GantiMudhakar Srivatsa
Published in: CoRR (2024)
Keyphrases
  • expert systems
  • machine learning
  • knowledge base
  • image processing
  • website
  • production line