Is there a best example of multithreading or WebApi?

[threerog]

Is YoloV8 object thread safe?
As is well known, it is very time-consuming to load the model for the first time. How to efficiently use YoloV8 when making concurrent calls in the form of multithreading or WebApi?
Can you provide some relevant examples or solutions?
For example, is it feasible to use lock or singleton patterns

[dme-compunet]

The internal logic of YoloV8 should be thread safe, however GPUs sometimes cannot perform inference in parallel, for this there is the property YoloV8parameters.SuppressParallelInference which when it is set to true the inference is performed inside a lock block, the preprocess and postprocess will still work in parallel to speed up the results.