Minor update on README, example notebooks and documentation (aws#216)

* Update generate_click_command inject logic to not expose unwanted flags to hyp-jumpstart-endpoint

* Update unit tests for bug fix, change --label_selector to --label-selector

* Update README, example notebooks and documentation to 1)remove model_version, 2)add --model-volume-mount-name 3)remove tar.gz from --model-location 4)update unique mount_path for --volume

* Update README, example notebooks and documentation to remove tls-config for jumpstart

* minor update to remove tar.gz from --model-location for documentation

Author: mollyheamazon

README.md

@@ -160,7 +160,7 @@ 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=/output_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:
@@ -181,7 +181,6 @@ 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
 ```
 
 
@@ -208,7 +207,8 @@ 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 \
@@ -322,20 +322,17 @@ 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",
     ")"
    ]
   },