Merge branch 'master' into master-update-apache-airflow

Author: benieric

CHANGELOG.md

@@ -1,5 +1,30 @@
 # Changelog
 
+## v2.243.0 (2025-03-27)
+
+### Features
+
+ * Enabled update_endpoint through model_builder
+
+### Bug Fixes and Other Changes
+
+ * Update for PT 2.5.1, SMP 2.8.0
+ * chore: move jumpstart region definitions to json file
+ * fix flaky clarify model monitor test
+ * fix flaky spark processor integ
+ * use temp file in unit tests
+ * Update transformers version
+ * Aligned disable_output_compression for @remote with Estimator
+ * Update Jinja version
+ * update image_uri_configs  03-26-2025 07:18:16 PST
+ * chore: fix integ tests to use latest version of model
+ * update image_uri_configs  03-25-2025 07:18:13 PST
+ * Skip tests failed due to deprecated instance type
+ * update image_uri_configs  03-21-2025 07:17:55 PST
+ * factor in set instance type when building JumpStart models in ModelBuilder.
+ * ADD Documentation to ReadtheDocs for Upgrading torch versions
+ * add new regions to JUMPSTART_LAUNCHED_REGIONS
+
 ## v2.242.0 (2025-03-14)
 
 ### Features

VERSION

@@ -1 +1 @@
-2.242.1.dev0
+2.243.1.dev0

doc/requirements.txt

@@ -2,7 +2,7 @@ sphinx==5.1.1
 sphinx-rtd-theme==0.5.0
 docutils==0.15.2
 packaging==20.9
-jinja2==3.1.4
+jinja2==3.1.6
 schema==0.7.5
 accelerate>=0.24.1,<=0.27.0
 graphene<4.0

requirements/extras/test_requirements.txt

@@ -20,7 +20,7 @@ attrs>=23.1.0,<24
 fabric==2.6.0
 requests==2.32.2
 sagemaker-experiments==0.1.35
-Jinja2==3.1.4
+Jinja2==3.1.6
 pyvis==0.2.1
 pandas==1.4.4
 scikit-learn==1.3.0
@@ -33,7 +33,7 @@ pillow>=10.0.1,<=11
 opentelemetry-proto==1.27.0
 protobuf==4.25.5
 tensorboard>=2.9.0,<=2.15.2
-transformers==4.46.1
+transformers==4.48.0
 sentencepiece==0.1.99
 # https://github.com/triton-inference-server/server/issues/6246
 tritonclient[http]<2.37.0

src/sagemaker/fw_utils.py

@@ -155,6 +155,7 @@
     "2.3.0",
     "2.3.1",
     "2.4.1",
+    "2.5.1",
 ]
 
 TRAINIUM_SUPPORTED_DISTRIBUTION_STRATEGIES = ["torch_distributed"]

src/sagemaker/image_uri_config/huggingface-llm-neuronx.json

@@ -9,7 +9,8 @@
             "2.2": "2.3.1",
             "2.2.0": "2.3.1",
             "2.3.1": "2.5.0",
-            "2.4.1": "2.7.0"
+            "2.4.1": "2.7.0",
+            "2.5.1": "2.8.0"
         },
         "versions": {
             "2.0.1": {
@@ -186,6 +187,31 @@
                     "us-west-2": "658645717510"
                 },
                 "repository": "smdistributed-modelparallel"
+            },
+            "2.8.0": {
+                "py_versions": [
+                    "py311"
+                ],
+                "registries": {
+                    "ap-northeast-1": "658645717510",
+                    "ap-northeast-2": "658645717510",
+                    "ap-northeast-3": "658645717510",
+                    "ap-south-1": "658645717510",
+                    "ap-southeast-1": "658645717510",
+                    "ap-southeast-2": "658645717510",
+                    "ca-central-1": "658645717510",
+                    "eu-central-1": "658645717510",
+                    "eu-north-1": "658645717510",
+                    "eu-west-1": "658645717510",
+                    "eu-west-2": "658645717510",
+                    "eu-west-3": "658645717510",
+                    "sa-east-1": "658645717510",
+                    "us-east-1": "658645717510",
+                    "us-east-2": "658645717510",
+                    "us-west-1": "658645717510",
+                    "us-west-2": "658645717510"
+                },
+                "repository": "smdistributed-modelparallel"
             }
         }
     }

src/sagemaker/image_uri_config/huggingface-llm.json

@@ -12,6 +12,7 @@
                 "ap-southeast-2": "452832661640",
                 "ap-southeast-3": "276181064229",
                 "ap-southeast-5": "148761635175",
+                "ap-southeast-7": "528757812139",
                 "ca-central-1": "310906938811",
                 "cn-north-1": "390048526115",
                 "cn-northwest-1": "390780980154",
@@ -26,6 +27,7 @@
                 "il-central-1": "380164790875",
                 "me-central-1": "103105715889",
                 "me-south-1": "117516905037",
+                "mx-central-1": "396913743851",
                 "sa-east-1": "782484402741",
                 "us-east-1": "081325390199",
                 "us-east-2": "429704687514",

src/sagemaker/image_uri_config/pytorch-smp.json

@@ -701,12 +701,16 @@ def get_training_image_uri(
             if "modelparallel" in distribution["smdistributed"]:
                 if distribution["smdistributed"]["modelparallel"].get("enabled", True):
                     framework = "pytorch-smp"
-                    if (
-                        "p5" in instance_type
-                        or "2.1" in framework_version
-                        or "2.2" in framework_version
-                        or "2.3" in framework_version
-                        or "2.4" in framework_version
+                    supported_smp_pt_versions_cu124 = ("2.5",)
+                    supported_smp_pt_versions_cu121 = ("2.1", "2.2", "2.3", "2.4")
+                    if any(
+                        pt_version in framework_version
+                        for pt_version in supported_smp_pt_versions_cu124
+                    ):
+                        container_version = "cu124"
+                    elif "p5" in instance_type or any(
+                        pt_version in framework_version
+                        for pt_version in supported_smp_pt_versions_cu121
                     ):
                         container_version = "cu121"
                     else: