@inproceedings{ko2024distillm,
author = {Ko, Jongwoo and Kim, Sungnyun and Chen, Tianyi and Yun, Se-Young},
title = {DistiLLM: Towards Streamlined Distillation for Large Language Models},
booktitle = {ICML 2024},
year = {2024},
month = {February},
abstract = {Knowledge distillation (KD) is widely used for compressing a teacher model to a smaller student model, reducing its inference cost and memory footprint while preserving model capabilities. However, current KD methods for auto-regressive sequence models (e.g., large language models) suffer from missing a standardized objective function. Moreover, the recent use of student-generated outputs to address training-inference mismatches has significantly escalated computational costs. To tackle these issues, we introduce DistiLLM, a more effective and efficient KD framework for auto-regressive language models. DistiLLM comprises two components: (1) a novel skew Kullback-Leibler divergence loss, where we unveil and leverage its theoretical properties, and (2) an adaptive off-policy approach designed to enhance the efficiency in utilizing student-generated outputs. Extensive experiments, including instruction-following tasks, demonstrate the effectiveness of DistiLLM in building high-performing student models while achieving up to 4.3$\times$ speedup compared to recent KD methods.},
url = {http://approjects.co.za/?big=en-us/research/publication/distillm-towards-streamlined-distillation-for-large-language-models/},
}