add new shape and exception handling

Author: VipulMascarenhas

ads/aqua/config/config.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
 # Copyright (c) 2024 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
@@ -14,5 +13,6 @@ def get_finetuning_config_defaults():
             "BM.GPU.A10.4": {"batch_size": 1, "replica": 1},
             "BM.GPU4.8": {"batch_size": 4, "replica": 1},
             "BM.GPU.A100-v2.8": {"batch_size": 6, "replica": 1},
+            "BM.GPU.H100.8": {"batch_size": 6, "replica": 1},
         }
     }

ads/aqua/config/deployment_config_defaults.json

@@ -31,6 +31,7 @@
     "BM.GPU.A10.4",
     "BM.GPU4.8",
     "BM.GPU.A100-v2.8",
+    "BM.GPU.H100.8",
     "VM.Standard.A1.Flex"
   ]
 }

ads/aqua/config/resource_limit_names.json

@@ -1,6 +1,7 @@
 {
   "BM.GPU.A10.4": "ds-gpu-a10-count",
   "BM.GPU.A100-v2.8": "ds-gpu-a100-v2-count",
+  "BM.GPU.H100.8": "ds-gpu-h100-count",
   "BM.GPU4.8": "ds-gpu4-count",
   "VM.GPU.A10.1": "ds-gpu-a10-count",
   "VM.GPU.A10.2": "ds-gpu-a10-count"

ads/aqua/evaluation/evaluation.py

@@ -7,7 +7,7 @@
 import re
 import tempfile
 from concurrent.futures import ThreadPoolExecutor, as_completed
-from dataclasses import asdict
+from dataclasses import asdict, fields
 from datetime import datetime, timedelta
 from pathlib import Path
 from threading import Lock
@@ -160,8 +160,9 @@ def create(
                 create_aqua_evaluation_details = CreateAquaEvaluationDetails(**kwargs)
             except Exception as ex:
                 raise AquaValueError(
-                    "Invalid create evaluation parameters. Allowable parameters are: "
-                    f"{', '.join(list(asdict(CreateAquaEvaluationDetails).keys()))}."
+                    "Invalid create evaluation parameters. "
+                    "Allowable parameters are: "
+                    f"{', '.join([field.name for field in fields(CreateAquaEvaluationDetails)])}."
                 ) from ex
 
         if not is_valid_ocid(create_aqua_evaluation_details.evaluation_source_id):
@@ -178,18 +179,28 @@ def create(
             evaluation_source = ModelDeployment.from_id(
                 create_aqua_evaluation_details.evaluation_source_id
             )
-            if evaluation_source.runtime.type == ModelDeploymentRuntimeType.CONTAINER:
-                runtime = ModelDeploymentContainerRuntime.from_dict(
-                    evaluation_source.runtime.to_dict()
+            try:
+                if (
+                    evaluation_source.runtime.type
+                    == ModelDeploymentRuntimeType.CONTAINER
+                ):
+                    runtime = ModelDeploymentContainerRuntime.from_dict(
+                        evaluation_source.runtime.to_dict()
+                    )
+                    inference_config = AquaContainerConfig.from_container_index_json(
+                        enable_spec=True
+                    ).inference
+                    for container in inference_config.values():
+                        if container.name == runtime.image.split(":")[0]:
+                            eval_inference_configuration = (
+                                container.spec.evaluation_configuration
+                            )
+            except Exception:
+                logger.debug(
+                    f"Could not load inference config details for the evaluation id: "
+                    f"{create_aqua_evaluation_details.evaluation_source_id}. Please check if the container"
+                    f" runtime has the correct SMC image information."
                 )
-                inference_config = AquaContainerConfig.from_container_index_json(
-                    enable_spec=True
-                ).inference
-                for container in inference_config.values():
-                    if container.name == runtime.image.split(":")[0]:
-                        eval_inference_configuration = (
-                            container.spec.evaluation_configuration
-                        )
         elif (
             DataScienceResource.MODEL
             in create_aqua_evaluation_details.evaluation_source_id
@@ -550,7 +561,7 @@ def _build_evaluation_runtime(
                                     metrics=metrics,
                                 ),
                             ),
-                            **inference_configuration,
+                            **(inference_configuration or {}),
                         },
                     ),
                     "CONDA_BUCKET_NS": CONDA_BUCKET_NS,