Domestic Chips
Using Huawei MindIE
07/30/202640771 views
First, select the PyTorch MindIE image based on your version requirements:

Then refer to Huawei’s documentation: Inference Service Deployment (DeepSeek-R1-Distill-Qwen-7B) - AI Service Deployment - Solution Deployment Guide - RAG Integrated Solution Reference Practice - Kunpeng RAG Development Documentation - Kunpeng Community
Huawei’s documentation streamlines the steps:
-
Prepare the model
-
Edit the
/usr/local/Ascend/mindie/latest/mindie-service/conf/config.jsonfile, primarily to modify the model paths and Device Index, among other things. It is also important to set thehttpsEnabledfield in the config file tofalse, as certificates are generally not used in this scenario. -
Load environment variables:
source /usr/local/Ascend/ascend-toolkit/set_env.sh
source /usr/local/Ascend/nnal/atb/set_env.sh
source /usr/local/Ascend/atb-models/set_env.sh
source /usr/local/Ascend/mindie/set_env.sh
source /usr/local/Ascend/mindie/latest/mindie-service/set_env.sh
- Start the service
cd /usr/local/Ascend/mindie/latest/mindie-service/bin
./mindieservice_daemon
