Merge branch 'main' into 404error

Author: mohamedzeidan2021

README.md

@@ -171,7 +171,7 @@ hyp create hyp-pytorch-job \
     --priority "high" \
     --max-retry 3 \
     --volume name=model-data,type=hostPath,mount_path=/data,path=/data \
-    --volume name=training-output,type=pvc,mount_path=/data,claim_name=my-pvc,read_only=false
+    --volume name=training-output,type=pvc,mount_path=/data2,claim_name=my-pvc,read_only=false
 ```
 
 Key required parameters explained:
@@ -192,7 +192,6 @@ hyp create hyp-jumpstart-endpoint \
     --model-id jumpstart-model-id\
     --instance-type ml.g5.8xlarge \
     --endpoint-name endpoint-jumpstart \
-    --tls-output-s3-uri s3://sample-bucket
 ```
 
 
@@ -219,7 +218,8 @@ hyp create hyp-custom-endpoint \
     --endpoint-name my-custom-endpoint \
     --model-name my-pytorch-model \
     --model-source-type s3 \
-    --model-location my-pytorch-training/model.tar.gz \
+    --model-location my-pytorch-training \
+    --model-volume-mount-name test-volume \
     --s3-bucket-name your-bucket \
     --s3-region us-east-1 \
     --instance-type ml.g5.8xlarge \
@@ -333,20 +333,17 @@ from sagemaker.hyperpod.inference.config.hp_jumpstart_endpoint_config import Mod
 from sagemaker.hyperpod.inference.hp_jumpstart_endpoint import HPJumpStartEndpoint
 
 model=Model(
-    model_id='deepseek-llm-r1-distill-qwen-1-5b',
-    model_version='2.0.4',
+    model_id='deepseek-llm-r1-distill-qwen-1-5b'
 )
 server=Server(
     instance_type='ml.g5.8xlarge',
 )
 endpoint_name=SageMakerEndpoint(name='<my-endpoint-name>')
-tls_config=TlsConfig(tls_certificate_output_s3_uri='s3://<my-tls-bucket>')
 
 js_endpoint=HPJumpStartEndpoint(
     model=model,
     server=server,
-    sage_maker_endpoint=endpoint_name,
-    tls_config=tls_config,
+    sage_maker_endpoint=endpoint_name
 )
 
 js_endpoint.create()

doc/inference.md

@@ -37,8 +37,7 @@ from sagemaker.hyperpod.inference.config.hp_jumpstart_endpoint_config import Mod
 from sagemaker.hyperpod.inference.hp_jumpstart_endpoint import HPJumpStartEndpoint
 
 model = Model(
-    model_id="deepseek-llm-r1-distill-qwen-1-5b",
-    model_version="2.0.4"
+    model_id="deepseek-llm-r1-distill-qwen-1-5b"
 )
 
 server = Server(
@@ -47,13 +46,10 @@ server = Server(
 
 endpoint_name = SageMakerEndpoint(name="endpoint-jumpstart")
 
-tls_config = TlsConfig(tls_certificate_output_s3_uri="s3://sample-bucket")
-
 js_endpoint = HPJumpStartEndpoint(
     model=model,
     server=server,
-    sage_maker_endpoint=endpoint_name,
-    tls_config=tls_config
+    sage_maker_endpoint=endpoint_name
 )
 
 js_endpoint.create()
@@ -85,7 +81,7 @@ from sagemaker.hyperpod.inference.hp_endpoint import HPEndpoint
 
 model = Model(
     model_source_type="s3",
-    model_location="test-pytorch-job/model.tar.gz",
+    model_location="test-pytorch-job",
     s3_bucket_name="my-bucket",
     s3_region="us-east-2",
     prefetch_enabled=True

examples/inference/SDK/inference-jumpstart-e2e.ipynb

@@ -107,21 +107,18 @@
    "source": [
     "# create configs\n",
     "model=Model(\n",
-    "    model_id='deepseek-llm-r1-distill-qwen-1-5b',\n",
-    "    model_version='2.0.4',\n",
+    "    model_id='deepseek-llm-r1-distill-qwen-1-5b'\n",
     ")\n",
     "server=Server(\n",
     "    instance_type='ml.g5.8xlarge',\n",
     ")\n",
     "endpoint_name=SageMakerEndpoint(name='<my-endpoint-name>')\n",
-    "tls_config=TlsConfig(tls_certificate_output_s3_uri='s3://<my-tls-bucket>')\n",
     "\n",
     "# create spec\n",
     "js_endpoint=HPJumpStartEndpoint(\n",
     "    model=model,\n",
     "    server=server,\n",
-    "    sage_maker_endpoint=endpoint_name,\n",
-    "    tls_config=tls_config,\n",
+    "    sage_maker_endpoint=endpoint_name\n",
     ")"
    ]
   },

hyperpod-custom-inference-template/hyperpod_custom_inference_template/v1_0/model.py

@@ -10,7 +10,7 @@
 # distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF
 # ANY KIND, either express or implied. See the License for the specific
 # language governing permissions and limitations under the License.
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, model_validator, ConfigDict
 from typing import Optional, List, Dict, Union, Literal
 
 from sagemaker.hyperpod.inference.config.hp_endpoint_config import (
@@ -31,9 +31,19 @@
 from sagemaker.hyperpod.inference.hp_endpoint import HPEndpoint
 
 class FlatHPEndpoint(BaseModel):
+    model_config = ConfigDict(extra="forbid")
+
+    metadata_name: Optional[str]  = Field(
+        None,
+        alias="metadata_name",
+        description="Name of the jumpstart endpoint object",
+        max_length=63,
+        pattern=r"^[a-zA-Z0-9](-*[a-zA-Z0-9]){0,62}$",
+    )
+
     # endpoint_name
     endpoint_name: Optional[str] = Field(
-        "",
+        None,
         alias="endpoint_name",
         description="Name of SageMaker endpoint; empty string means no creation",
         max_length=63,
@@ -130,7 +140,7 @@ class FlatHPEndpoint(BaseModel):
         description="FSX File System DNS Name",
     )
     fsx_file_system_id: Optional[str] = Field(
-        ...,  
+        None,  
         alias="fsx_file_system_id",
         description="FSX File System ID",
     )
@@ -142,12 +152,12 @@ class FlatHPEndpoint(BaseModel):
 
     # S3Storage
     s3_bucket_name: Optional[str] = Field(
-        ..., 
+        None, 
         alias="s3_bucket_name",
         description="S3 bucket location",
     )
     s3_region: Optional[str] = Field(
-        ..., 
+        None, 
         alias="s3_region",
         description="S3 bucket region",
     )
@@ -229,12 +239,22 @@ class FlatHPEndpoint(BaseModel):
     invocation_endpoint: Optional[str] = Field(
         default="invocations",
         description=(
-            "The invocation endpoint of the model server. "
-            "http://<host>:<port>/ would be pre-populated based on the other fields. "
+            "The invocation endpoint of the model server. http://<host>:<port>/ would be pre-populated based on the other fields. "
             "Please fill in the path after http://<host>:<port>/ specific to your model server.",
         )
     )
-
+    
+    @model_validator(mode='after')
+    def validate_model_source_config(self):
+        """Validate that required fields are provided based on model_source_type"""
+        if self.model_source_type == "s3":
+            if not self.s3_bucket_name or not self.s3_region:
+                raise ValueError("s3_bucket_name and s3_region are required when model_source_type is 's3'")
+        elif self.model_source_type == "fsx":
+            if not self.fsx_file_system_id:
+                raise ValueError("fsx_file_system_id is required when model_source_type is 'fsx'")
+        return self
+    
     def to_domain(self) -> HPEndpoint:
         env_vars = None
         if self.env: