DeepEP

DeepEP is a GPU communication library for expert parallelism in MoE models, released by DeepSeek in 2025.

1 articleLast mentioned

DeepEP is an open-source communication library developed by the Chinese AI company DeepSeek. It is designed to accelerate the all-to-all communication used in expert parallelism, where a Mixture of Experts (MoE) model is spread across multiple GPUs and tokens must be dispatched to the GPUs holding each expert and gathered back. It was released in February 2025 during DeepSeek's open-source week.

It supports both NVLink within a server and RDMA between servers, and provides separate high-throughput kernels for training and prefill and low-latency kernels for decoding. It is one of the libraries on which DeepSeek's inference engine DeepInfer is built.

This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.

Articles covering this entry

  • DeepSeek Opens DeepInfer Serving Engine Alongside MIT-Licensed V4.1-FlashAI News ·

    DeepEP, kernels for expert parallelism

    Read article

Found a mistake or missing an entry?

Wiki entries are based on AIPOST articles and widely known facts. If an entry is wrong, send us a correction request and we will check and fix it. Names from new articles are added to the wiki after the article is published.