#artificial intelligence
Feb 2026
MineDraft: A Framework for Batch Parallel Speculative Decoding
MineDraft, a batch parallel speculative decoding framework designed to effectively hide drafting latency by overlapping it with verification, is proposed, and the theoretical analysis shows that PSD is substantially more efficient than standard SD.
Zhenwei Tang, A. Verma, Zijian Zhou et al.
· arXiv.org · 2 citations