Papers
arxiv:2403.00835

CLLMs: Consistency Large Language Models

Published on Feb 28
Authors:
,
,
,

Abstract

Parallel decoding methods such as Jacobi decoding show promise for more efficient LLM inference as it breaks the sequential nature of the LLM decoding process and transforms it into parallelizable computation. However, in practice, it achieves little speedup compared to traditional autoregressive (AR) decoding, primarily because Jacobi decoding seldom accurately predicts more than one token in a single fixed-point iteration step. To address this, we develop a new approach aimed at realizing fast convergence from any state to the fixed point on a Jacobi trajectory. This is accomplished by refining the target LLM to consistently predict the fixed point given any state as input. Extensive experiments demonstrate the effectiveness of our method, showing 2.4times to 3.4times improvements in generation speed while preserving generation quality across both domain-specific and open-domain benchmarks.

Community

Interesting 'denoising'-based parallel generation approach.

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2403.00835 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2403.00835 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2403.00835 in a Space README.md to link it from this page.

Collections including this paper 1