Pinned Loading

1. MC-SMoE MC-SMoE Public

   [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"

   Python 102 12

2. Flex-MoE Flex-MoE Public

   [NeurIPS 2024 Spotlight] Code for the paper "Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts"

   Python 70 10

3. Mew Mew Public

   [ECCV 2024] Code for the paper "Mew: Multiplexed Immunofluorescence Image Analysis through an Efficient Multiplex Network"

   Python 17

4. C2R-MoE C2R-MoE Public

   [NAACL'25 🏆 SAC Award] Official code for "Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert Parallelism Design"

   Python 15

5. HEXA-MoE HEXA-MoE Public

   Official code for the paper "HEXA-MoE: Efficient and Heterogeneous-Aware MoE Acceleration with Zero Computation Redundancy"

   Python 15 2

6. Occult Occult Public

   [ICML‘25] Official code for paper "Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training and Inference"

   Python 13