GitHub user Xuanwo edited a discussion: New Users: Expert Kit, A Distributed, 
Expert-Centric Framework for MoE LLM Inference

https://github.com/expert-kit/expert-kit


They are using opendal to save/load tensors from local fs or s3.

---

`Expert Kit (EK)` is a high-performance framework for scalable MoE (Mixture of 
Experts) LLM inference. The vision of EK is to provide an efficient foundation 
of Expert Parallelism (EP) on heterogeneous hardware (e.g., CPU and GPU) over 
commodity networks (e.g. PCIe, TCP, RDMA), thereby enabling easy deployment and 
fine-grained expert-level scaling.

![image](https://github.com/user-attachments/assets/ea9649a9-a1e1-4bd6-a109-8a58f2f8734c)


GitHub link: https://github.com/apache/opendal/discussions/6153

----
This is an automatically sent email for [email protected].
To unsubscribe, please send an email to: [email protected]

Reply via email to