I think I understand. In general, if your communication worked without clearml, it should also work when using clearml.
But you won't be able to upload an artifact using None for example, to the shared memory. Same thing for debug samples etc.
instead of transferring the entire image
This can be any type of preprocessing data(image, audio, bytearray)
sorry just a q question, so we do not need to do much in our end right? I mean clearml will handle sharing memory between the process.py and triton server?
I am honestly not sure if it will work, but we do have a http driver that could query your endpoint. None
It's worth to give it a try
Hi @<1657918706052763648:profile|SillyRobin38> ! If it is compatible with http/rest, you could try setting api.files_server to the endpoint or sdk.storage.default_output_uri in clearml.conf (depending on your use-case).
Thanks for sharing that but If I'm not mistaken, I couldn't share my exact issue here. Shared memory will also utilize the same communications as HTTP/RPC. However, instead of transferring the entire image, for example, to the Triton server, it will bind the image's address to some shared memory and then send the address using HTTP to the Triton server. By doing this, we can save the cost of transferring data. Please correct me if I'm wrong about this. I want to know if clearml can support such a thing at the moment?
Thanks @<1523701435869433856:profile|SmugDolphin23>