all AI news
Speculative Streaming: Fast LLM Inference without Auxiliary Models
Feb. 20, 2024, 5:43 a.m. | Nikhil Bhendawade, Irina Belousova, Qichen Fu, Henry Mason, Mohammad Rastegari, Mahyar Najibi
cs.LG updates on arXiv.org arxiv.org
Abstract: Speculative decoding is a prominent technique to speed up the inference of a large target language model based on predictions of an auxiliary draft model. While effective, in application-specific settings, it often involves fine-tuning both draft and target models to achieve high acceptance rates. As the number of downstream tasks grows, these draft models add significant complexity to inference systems. We propose Speculative Streaming, a single-model speculative decoding method that fuses drafting into the target …
abstract application arxiv cs.ai cs.cl cs.lg decoding draft fine-tuning inference language language model llm predictions speed streaming type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Risk Management - Machine Learning and Model Delivery Services, Product Associate - Senior Associate-
@ JPMorgan Chase & Co. | Wilmington, DE, United States
Senior ML Engineer (Speech/ASR)
@ ObserveAI | Bengaluru