all AI news
Accelerating Speculative Decoding using Dynamic Speculation Length
May 8, 2024, 4:47 a.m. | Jonathan Mamou, Oren Pereg, Daniel Korat, Moshe Berchansky, Nadav Timor, Moshe Wasserblat, Roy Schwartz
cs.CL updates on arXiv.org arxiv.org
Abstract: Speculative decoding is a promising method for reducing the inference latency of large language models. The effectiveness of the method depends on the speculation length (SL) - the number of tokens generated by the draft model at each iteration. The vast majority of speculative decoding approaches use the same SL for all iterations. In this work, we show that this practice is suboptimal. We introduce DISCO, a DynamIc SpeCulation length Optimization method that uses a …
abstract arxiv cs.cl decoding draft dynamic generated inference inference latency iteration language language models large language large language models latency speculation tokens type vast
More from arxiv.org / cs.CL updates on arXiv.org
ALBA: Adaptive Language-based Assessments for Mental Health
2 days, 13 hours ago |
arxiv.org
PACE: Improving Prompt with Actor-Critic Editing for Large Language Model
2 days, 13 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US