Run online model inference which returns the model output directly.
Run online model inference which returns the model output directly. This method is used in fetcher.fetchJoin to process the model inference
RunModelInferenceResponse containing the model outputs for the given inputs.
Run batch model inference job which will be executed asynchronously in batch.
Run batch model inference job which will be executed asynchronously in batch.
a job ID that can be used to check the status of the job.