Speculative Streaming: Fast LLM Inference without Auxiliary Models
Paper
•
2402.11131
•
Published
•
41
llm/speculative-decoding
-
-
Ouroboros: Speculative Decoding with Large Model Enhanced Drafting
Paper • 2402.13720 • Published • 5 -
Recurrent Drafter for Fast Speculative Decoding in Large Language Models
Paper • 2403.09919 • Published • 20 -
On Speculative Decoding for Multimodal Large Language Models
Paper • 2404.08856 • Published • 13