In MLServer, each loaded model can be configured separately . This configuration will include model information (e.g. metadata about the accepted inputs), but ...
18
/en/stable/reference...
Codecs are used to encapsulate the logic required to encode / decode payloads following the Open Inference Protocol into high-level Python types.
25
/en/latest/examples/...
MLServer has been built with Multi-Model Serving (MMS) in mind . This means that, within a single instance of MLServer, you can serve multiple models under ...