The performance of using OpenVINO Model Server is much lower than deploying locally

[WT_Jacko]

Hi all,

When I run models using OVMS, I find that CPU or GPU utilization is much lower than when deployed locally.

Please refer to link in attachment; the video of the test results and my configuration are included.

Thanks

Best Regards

Jacko

[Zulkifli_Intel]

WT_Jacko,

Thank you for reaching out,

I noticed that you had opened a new thread with a similar issue. Therefore I'll close this thread and we will continue the discussion in this thread:

https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/The-performance-of-using-OpenVINO-Model-Server-is-much-lower/m-p/1616335#M31199

Regards,

Zul