Resolving conflicts

Author: kumar-shivam-ranjan

.github/workflows/run-forecast-unit-tests.yml

@@ -27,7 +27,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10"]
+        python-version: ["3.9", "3.10", "3.11"]
 
     steps:
       - uses: actions/checkout@v4

.github/workflows/run-operators-unit-tests.yml

@@ -27,7 +27,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.9", "3.10", "3.11"]
 
     steps:
       - uses: actions/checkout@v4

THIRD_PARTY_LICENSES.txt

@@ -483,6 +483,11 @@ rrcf
 * Source code: https://github.com/kLabUM/rrcf
 * Project home: https://github.com/kLabUM/rrcf
 
+Merlion
+* Copyright 2021 Salesforce.com Inc
+* License: BSD-3 Clause License
+* Source code: https://github.com/salesforce/Merlion
+* Project Home: https://github.com/salesforce/Merlion
 
 =============================== Licenses ===============================
 ------------------------------------------------------------------------

ads/aqua/common/utils.py

@@ -1071,7 +1071,6 @@ def list_hf_models(query: str) -> List[str]:
     try:
         models = HfApi().list_models(
             model_name=query,
-            task="text-generation",
             sort="downloads",
             direction=-1,
             limit=20,

ads/aqua/config/config.py

@@ -40,6 +40,7 @@ def get_finetuning_config_defaults():
             "VM.GPU.A10.2": {"batch_size": 1, "replica": "1-10"},
             "BM.GPU.A10.4": {"batch_size": 1, "replica": 1},
             "BM.GPU4.8": {"batch_size": 4, "replica": 1},
+            "BM.GPU.L40S-NC.4": {"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

@@ -30,6 +30,7 @@
     "VM.GPU.A10.2",
     "BM.GPU.A10.4",
     "BM.GPU4.8",
+    "BM.GPU.L40S-NC.4",
     "BM.GPU.A100-v2.8",
     "BM.GPU.H100.8",
     "VM.Standard.A1.Flex"

ads/aqua/config/resource_limit_names.json

@@ -2,6 +2,7 @@
   "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.GPU.L40S-NC.4": "ds-gpu-l40s-nc-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/extension/deployment_handler.py

@@ -102,6 +102,7 @@ def post(self, *args, **kwargs):
         ocpus = input_data.get("ocpus")
         memory_in_gbs = input_data.get("memory_in_gbs")
         model_file = input_data.get("model_file")
+        private_endpoint_id = input_data.get("private_endpoint_id")
 
         self.finish(
             AquaDeploymentApp().create(
@@ -124,6 +125,7 @@ def post(self, *args, **kwargs):
                 ocpus=ocpus,
                 memory_in_gbs=memory_in_gbs,
                 model_file=model_file,
+                private_endpoint_id=private_endpoint_id,
             )
         )
 

ads/aqua/modeldeployment/deployment.py

@@ -103,6 +103,7 @@ def create(
         memory_in_gbs: Optional[float] = None,
         ocpus: Optional[float] = None,
         model_file: Optional[str] = None,
+        private_endpoint_id: Optional[str] = None,
     ) -> "AquaDeployment":
         """
         Creates a new Aqua deployment
@@ -149,6 +150,9 @@ def create(
             The ocpu count for the shape selected.
         model_file: str
             The file used for model deployment.
+        private_endpoint_id: str
+            The private endpoint id of model deployment.
+
         Returns
         -------
         AquaDeployment
@@ -171,6 +175,7 @@ def create(
                 tags[tag] = aqua_model.freeform_tags[tag]
 
         tags.update({Tags.AQUA_MODEL_NAME_TAG: aqua_model.display_name})
+        tags.update({Tags.TASK: aqua_model.freeform_tags.get(Tags.TASK, None)})
 
         # Set up info to get deployment config
         config_source_id = model_id
@@ -341,6 +346,7 @@ def create(
             .with_bandwidth_mbps(bandwidth_mbps)
             .with_replica(instance_count)
             .with_web_concurrency(web_concurrency)
+            .with_private_endpoint_id(private_endpoint_id)
             .with_access_log(
                 log_group_id=log_group_id,
                 log_id=access_log_id,

ads/aqua/modeldeployment/entities.py

@@ -3,7 +3,7 @@
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
 from dataclasses import dataclass, field
-from typing import Union
+from typing import Union, Optional
 
 from oci.data_science.models import (
     ModelDeployment,
@@ -47,9 +47,10 @@ class AquaDeployment(DataClassSerializable):
     created_on: str = None
     created_by: str = None
     endpoint: str = None
+    private_endpoint_id: str = None
     console_link: str = None
     lifecycle_details: str = None
-    shape_info: field(default_factory=ShapeInfo) = None
+    shape_info: Optional[ShapeInfo] = None
     tags: dict = None
     environment_variables: dict = None
 
@@ -98,6 +99,7 @@ def from_oci_model_deployment(
         freeform_tags = oci_model_deployment.freeform_tags or UNKNOWN_DICT
         aqua_service_model_tag = freeform_tags.get(Tags.AQUA_SERVICE_MODEL_TAG, None)
         aqua_model_name = freeform_tags.get(Tags.AQUA_MODEL_NAME_TAG, UNKNOWN)
+        private_endpoint_id = getattr(instance_configuration, "private_endpoint_id", UNKNOWN)
 
         return AquaDeployment(
             id=oci_model_deployment.id,
@@ -113,6 +115,7 @@ def from_oci_model_deployment(
             created_on=str(oci_model_deployment.time_created),
             created_by=oci_model_deployment.created_by,
             endpoint=oci_model_deployment.model_deployment_url,
+            private_endpoint_id=private_endpoint_id,
             console_link=get_console_link(
                 resource="model-deployments",
                 ocid=oci_model_deployment.id,