arXiv Open Access 2024

Dynamic Depth Decoding: Faster Speculative Decoding for LLMs

Oscar Brown Zhengjie Wang Andrea Do Nikhil Mathew Cheng Yu
Lihat Sumber

Abstrak

The acceleration of Large Language Models (LLMs) with speculative decoding provides a significant runtime improvement without any loss of accuracy. Currently, EAGLE-2 is the state-of-the-art speculative decoding method, improving on EAGLE with a dynamic draft tree. We introduce Dynamic Depth Decoding (DDD), which optimises EAGLE-2's tree drafting method using a dynamic depth. This extends the average speedup that EAGLE-2 achieves over EAGLE by $44\%$, giving DDD an average speedup of $3.16$x.

Topik & Kata Kunci

Penulis (5)

O

Oscar Brown

Z

Zhengjie Wang

A

Andrea Do

N

Nikhil Mathew

C

Cheng Yu

Format Sitasi

Brown, O., Wang, Z., Do, A., Mathew, N., Yu, C. (2024). Dynamic Depth Decoding: Faster Speculative Decoding for LLMs. https://arxiv.org/abs/2409.00142

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2024
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓