SyncAI.news, a Varaisys broadcasting
SilverSpoon-KD: A General-Purpose Toolkit for Knowledge Distillation
XR

Xaver R. Davey, David Broman

· 1 min read

ResearcharXiv cs.LG

SilverSpoon-KD: A General-Purpose Toolkit for Knowledge Distillation

arXiv:2611.22842v1 Announce Type: new Abstract: Knowledge distillation transfers deep learning representations from a teacher model to a student model, typically reducing model size or inference cost. However, knowledge distillation tooling has not kept pace with the breadth of research methods: existing toolkits typically support only a limited subset of techniques and use cases. We present SilverSpoon-KD, an open-source PyTorch toolkit that unifies different distillation paradigms and architectural relationships across workloads and applications behind a single API. Moreover, SilverSpoon-KD offers the first general-purpose blockwise knowledge distillation implementation with unique scalability features. We validate its versatility across vision, masked language model, and causal language models on tasks spanning homogeneous, heterogeneous, and quantization distillation across paradigms. We also evaluate SilverSpoon-KD by comparing its performance, including throughput and GPU memory usage, with existing toolkits. Despite extensive support for convenience, metric calculation, and tracking, we have found SilverSpoon-KD's performance to be on par with or better than existing toolkits.

Original source

This story was published by arXiv cs.LG and written by Xaver R. Davey, David Broman. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News