3D-MoE: Accelerating Multi-Expert Activated LLMs on 3D In/Near-Memory Computing Architecture via Hybrid Parallelism

Xinyu Qu, Zehua Zhang, Runnan Xu, Yufei Ma 0002. 3D-MoE: Accelerating Multi-Expert Activated LLMs on 3D In/Near-Memory Computing Architecture via Hybrid Parallelism. In IEEE/ACM International Conference On Computer Aided Design, ICCAD 2025, Munich, Germany, October 26-30, 2025. pages 1-9, IEEE, 2025. [doi]

References

No references recorded for this publication.

Cited by

No citations of this publication recorded.