Goldcrest: Full-Pipeline LLM Compression Framework for Low-Rank Factorization

Read full text Summarise with VIRAT
Authors: Mingxue Xu, Danilo P. Mandic
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

A LLM compression framework focusing on low-rank factorization (matrices and tensors), taking charge the whole experiment pipelines - compression, evaluation, profiling and logging. PyPi URL: https://pypi.org/project/goldcrest/

Fields of Study & Subjects

Advanced Neural Network Applications Topic Modeling Domain Adaptation and Few-Shot Learning

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
25 March 2026
Language
EN