Pinned Loading

1. CASE-Lab-UMD/LLM-Drop CASE-Lab-UMD/LLM-Drop Public

   The official implementation of the paper "What Matters in Transformers? Not All Attention is Needed".

   Python 186 22

2. CASE-Lab-UMD/Unified-MoE-Compression CASE-Lab-UMD/Unified-MoE-Compression Public

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

   Python 87 6

3. CASE-Lab-UMD/Router-Tuning-Mixture-of-Depths CASE-Lab-UMD/Router-Tuning-Mixture-of-Depths Public

   The open-source Mixture of Depths code and the official implementation of the paper "Router-Tuning: A Simple and Effective Approach for Enabling Dynamic Depth in Transformers. (EMNLP 2025)"

   Python 26 3

4. SparseUnifiedModel SparseUnifiedModel Public

   The official implementation of the paper "Understanding and Harnessing Sparsity in Unified Multimodal Models".

   Python 19

5. CASE-Lab-UMD/Capacity-Aware-MoE CASE-Lab-UMD/Capacity-Aware-MoE Public

   The official implementation of the paper "Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts".

   Python 11

6. MEO MEO Public

   The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":

   Python 44 4