Cointime

Download App
iOS & Android

DeepSeek-V3.2-Exp model officially released and open sourced

DeepSeek-V3.2-Exp model has been officially released and open-sourced. The model introduces a sparse Attention architecture, which can effectively reduce computational resource consumption and improve model inference efficiency. Currently, the model has been officially listed on the Huawei Cloud Model as a Service platform MaaS. For the DeepSeek-V3.2-Exp model, Huawei Cloud continues to use the large EP parallel deployment solution, based on the sparse Attention structure to achieve long sequence affinity with context parallel strategy, while also considering model latency and throughput performance.

Comments

All Comments

Recommended for you