← Search

Fangcheng Liu

2 accepted papers

2024

Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting

NeurIPS 2024poster

Speculative decoding has demonstrated its effectiveness in accelerating the inference of large language models (LLMs) while maintaining an identical sampling distribution. However, the conventional approach of training separate draft model to achieve a satisfactory token acceptance rate can be costl…

2024

Rethinking Optimization and Architecture for Tiny Language Models

ICML 2024poster

The power of large language models (LLMs) has been demonstrated through numerous data and computing resources. However, the application of language models on mobile devices is facing huge challenge on the computation and memory costs, that is, tiny language models with high performance are urgently…