You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Add a new mlserver-mlflow runtime which allows a user to point to a MLflow Model artifact (or folder) to load a model. As a initial step, the mlserver-mlflow runtime should take care of converting the V2 Dataplane payload to a "dict of tensors", which is one of the formats expected by MLflow models.
To translate this, we could just turn the V2 input into an "index", where the keys would be the inputs[].name fields. That is, an input such as:
While some MLflow models require their inputs to be encoded as dataframes, some others will still need a dictionary of tensors (see #160). To account for this, the scope of this issue includes looking at ways to infer which type of input does a model require, as well as providing a way for the user to choose which input type to use.
The latter could be done through the V2 Protocol's inputs[].parameters field, by setting a "magic key" (e.g. mlflow_encoding: dataframe). This key can then be read by the mlserver-mlflow runtime to choose one encoding or the other.
The text was updated successfully, but these errors were encountered:
Add a new
mlserver-mlflow
runtime which allows a user to point to a MLflow Model artifact (or folder) to load a model. As a initial step, themlserver-mlflow
runtime should take care of converting the V2 Dataplane payload to a "dict of tensors", which is one of the formats expected by MLflow models.To translate this, we could just turn the V2 input into an "index", where the keys would be the
inputs[].name
fields. That is, an input such as:, could be turned to the following MLflow-compatible dictionary of tensors:
Tensors vs Dataframes
While some MLflow models require their inputs to be encoded as dataframes, some others will still need a dictionary of tensors (see #160). To account for this, the scope of this issue includes looking at ways to infer which type of input does a model require, as well as providing a way for the user to choose which input type to use.
The latter could be done through the V2 Protocol's
inputs[].parameters
field, by setting a "magic key" (e.g.mlflow_encoding: dataframe
). This key can then be read by themlserver-mlflow
runtime to choose one encoding or the other.The text was updated successfully, but these errors were encountered: