Speculative Streaming: Fast LLM Inference without Auxiliary Models
Paper
•
2402.11131
•
Published
•
42
Rifky Bujana Bisri
Rifky
AI & ML interests
Natural Language Processing, BERT, Extractive Model, Reinforcement Learning, Indonesian Model
Recent Activity
updated
a model
8 days ago
Rifky/Indobert-QA
Organizations
