Currently MLServer can't deal well with models that are loaded on the same inference pool with other models that are heavy used. In this case there is a risk of starvation and we want to allow the user to be able to create models on separate processes (different inference pool).

MLServer does this but only if the model uses a specific custom environment tarball.

Proposed solution: Introduce inference_pool_gid to the ModelParameters class. In this way, we give the user the option to add the model to a dedicated inference pool group. Note that this allows to add either a single model or multiple models to the same group. I also included the autogenerate_inference_pool_gid boolean flag. When set to True and no inference_pool_gid is provided, a gid is generated using uuid4. This will add the model to a dedicated group - this way the user does not have to specify the gid themself.