https://github.com/CASE-Lab-UMD/Unified-MoE-Compression

The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".
https://github.com/CASE-Lab-UMD/Unified-MoE-Compression

deep-learning large-language-models machine-learning mixture-of-experts model-compression natural-language-processing

Last synced: 10 months ago
JSON representation

The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".

Host: GitHub
URL: https://github.com/CASE-Lab-UMD/Unified-MoE-Compression
Owner: CASE-Lab-UMD
License: apache-2.0
Created: 2024-02-24T17:21:26.000Z (about 2 years ago)
Default Branch: master
Last Pushed: 2025-03-17T14:21:30.000Z (12 months ago)
Last Synced: 2025-03-17T15:39:48.851Z (12 months ago)
Topics: deep-learning, large-language-models, machine-learning, mixture-of-experts, model-compression, natural-language-processing
Language: Python
Homepage:
Size: 47.1 MB
Stars: 60
Watchers: 1
Forks: 5
Open Issues: 0
Metadata Files:
- Readme: README.md
- License: LICENSE

ecosyste.ms