forked from docs/doc-exports
Lai, Weijian
4e4b2d5f6d
Reviewed-by: Hasko, Vladimir <vladimir.hasko@t-systems.com> Co-authored-by: Lai, Weijian <laiweijian4@huawei.com> Co-committed-by: Lai, Weijian <laiweijian4@huawei.com>
1.7 KiB
1.7 KiB
Model Deployment
ModelArts is capable of managing models and services. This allows mainstream framework images and models from multiple vendors to be managed in a unified manner.
Generally, AI model deployment and large-scale implementation are complex.
Figure 1 Process of deploying a model
- The real-time inference service features high concurrency, low latency, and elastic scaling, and supports multi-model gray release and A/B testing.
- ModelArts is optimized based on the high-performance AI inference chip Ascend 310. It can process PBs of inference data within a single day, publish over 1 million inference APIs on the cloud, and control inference network latency to milliseconds.
Parent topic: Basic Knowledge