GitHub · Python
CASE-Lab-UMD/Unified-MoE-Compression
The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".
- Stars
- 93
- Forks
- 7
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: deep-learning, large-language-models, machine-learning, mixture-of-experts, model-compression, natural-language-processing
Latest data point: Nov 21, 2026 · 93 stars · 7 forks