The time of multi-process calls to openvino in 2024 has skyrocketed, for example, when two processes call openvino to deploy the same model, the time of a single inference has doubled. What should I do about it
Which OpenVINO sample application/code are you using?
Which model are you using for this use case? (if possible, please help to share details of model(eg custom model/pretrained model), relevant model files and conversion steps that you did)
Your OS and hardware details
How did you measure the processing time?
What is your expected time/benchmark timing for the processing?
Does this recently happened where previously it work as expected?
Thank you for your question. If you need any additional information from Intel, please submit a new question as Intel is no longer monitoring this thread.
