تقرير
CLLMs: Consistency Large Language Models
| العنوان: | CLLMs: Consistency Large Language Models |
|---|---|
| المؤلفون: | Kou, Siqi, Hu, Lanxiang, He, Zhezhi, Deng, Zhijie, Zhang, Hao |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Artificial Intelligence |
| الوصف: | 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 2.4$\times$ to 3.4$\times$ improvements in generation speed while preserving generation quality across both domain-specific and open-domain benchmarks. Comment: In the proceedings of the 41st International Conference on Machine Learning (ICML) 2024 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2403.00835 |
| رقم الأكسشن: | edsarx.2403.00835 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |