Abstract
Large language models have shown impressive capabilities across a variety of NLP tasks, yet their generating text autoregressively is time-consuming. One way to speed them up is speculative decoding, which generates candidate segments (a sequence of tokens) from a fast draft model that is then verified in parallel by the target model. However, the acceptance rate of candidate tokens receives limitations from several factors, such as the model, the dataset, and the decoding setup. This paper proposes sampling multiple candidates from a draft model and then organising them in batches for verification. We design algorithms for efficient multi-candidate verification while maintaining the distribution of the target model. Our approach shows significant improvements in acceptance rates on multiple datasets and models, consistently outperforming standard speculative decoding.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- SDSAT: Accelerating LLM Inference through Speculative Decoding with Semantic Adaptive Tokens (2024)
- On Speculative Decoding for Multimodal Large Language Models (2024)
- Lossless Acceleration of Large Language Model via Adaptive N-gram Parallel Decoding (2024)
- Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting (2024)
- Clover: Regressive Lightweight Speculative Decoding with Sequential Knowledge (2024)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 8
Browse 8 models citing this paperDatasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper