Merge branch 'main' into feature/langchain

Author: VipulMascarenhas

.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/evaluation/evaluation_service_config.py

@@ -224,6 +224,7 @@ def search_shapes(
 
     class Config:
         extra = "ignore"
+        protected_namespaces = ()
 
 
 class EvaluationServiceConfig(Serializable):

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/constants.py

@@ -27,6 +27,7 @@
 LIFECYCLE_DETAILS_MISSING_JOBRUN = "The associated JobRun resource has been deleted."
 READY_TO_DEPLOY_STATUS = "ACTIVE"
 READY_TO_FINE_TUNE_STATUS = "TRUE"
+PRIVATE_ENDPOINT_TYPE = "MODEL_DEPLOYMENT"
 AQUA_GA_LIST = ["id19sfcrra6z"]
 AQUA_MODEL_TYPE_SERVICE = "service"
 AQUA_MODEL_TYPE_CUSTOM = "custom"

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,
             )
         )