Damian Kalinowski

@hwc0919 What do you mean with async stream API, can you elaborate? About the own thread pool - I don't think it is good idea to spin up separate thread...

@hwc0919 do you mean I should not run cpu intensive workloads in this lambda? https://github.com/drogonframework/drogon/blob/master/examples/helloworld/main.cc#L20-L26 This is what I meant

> drogon's internal pool is for non-blocking fast io operations, not for cpu intensive workload or blocking operations. You will block incoming connections if you block those threads. This is...

Any hints? Is it not supported?

It is valid use case for our library users to use C-API to stop and re-start the server with different parameters within the same process. I understand Drogon is not...

> Are you sure there are no functional downsides No functional downsides visible in simple & multiple datasets > I'm not a fan of creating specific chat template for particular...

@dtrawins I already tried doing that in this PR: https://github.com/openvinotoolkit/model_server/pull/3854 However, after installing python 3.12 and trying to use that for model export I found another issues (described in the...

> #2191 This PR added ability to check the connection state in case we have access to http request object. The issue is related to scenario when there is no...

@nqf even if you can check connection status the way you described, we still have no way to get disconnection information when workload is blocking. The example would be running...

Yes, consider the example be slightly modified: ``` app().registerHandler( "/stream", [](const HttpRequestPtr & ptr, std::function &&callback) { std::thread([=] { my_workload->run(); // blocking for 10 minutes }).detach(); ``` If we would...