← Search

Kaihuo Zhang

2 accepted papers

2025

FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling

ACL 2025long

Speculative sampling has emerged as an important technique for accelerating the auto-regressive generation process of large language models (LLMs) by utilizing a draft-then-verify mechanism to produce multiple tokens per forward pass. While state-of-the-art speculative sampling methods use only a si…

2024

Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding

EMNLP 2024main

Speculative decoding is a widely used method that accelerates the generation process of large language models (LLMs) with no compromise in model performance. It achieves this goal by using an existing smaller model for drafting and then employing the target LLM to verify the draft in a low-cost para…