diff --git a/CHANGELOG.md b/CHANGELOG.md index b5ddd688..5f957f09 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,32 @@ # Changelog +## v3.7.1 (2026-04-08) + +### New Instance Type Support +- Add g7e instance types to HyperPod helm chart values (nvidia/EFA device plugins) (#380) +- Add g7e instance types to Python constants and CLI (#385, #390) +- Add g7e instance types to health-monitoring-agent node affinity (#381) +- Add B300 MIG profiles to GPU operator ConfigMap (#396) +- Add MIG profile support for ml.p6-b300.48xlarge (Blackwell Ultra) (#398) + +### Inference Operator +- CRD updates: BYO certificate, RequestLimitsConfig, Custom Kubernetes support (#402) +- Bump hyperpod-inference-operator subchart to v2.1.0 with image tag v3.1 (#402) + +### Enhancements +- Support AWS_REGION env var, cluster context fallback, centralize boto3 client creation (#395) +- Handle pagination in cluster stack listing (#394) +- Require --instance-type when specifying accelerator resources (#393) + +### Bug Fixes +- Fix EFA field naming in PyTorch job template v1.1: `efa_interfaces` -> `efa`, `efa_interfaces_limit` -> `efa_limit` (#392) +- Fix deep health check nodeSelector label to `sagemaker.amazonaws.com/deep-health-check-status: Passed` (#386) +- Remove non-EFA instance types from EFA device plugin nodeAffinity to prevent CrashLoopBackOff (#389) +- Add missing instance types and fix EFA/memory resource specs (#385) + +### Health Monitoring Agent +- Release Health Monitoring Agent 1.0.1434.0_1.0.388.0 (#388) + ## v3.7.0 (2026-03-02) Space CLI diff --git a/hyperpod-pytorch-job-template/CHANGELOG.md b/hyperpod-pytorch-job-template/CHANGELOG.md index b04f9bc3..fa7ae2c2 100644 --- a/hyperpod-pytorch-job-template/CHANGELOG.md +++ b/hyperpod-pytorch-job-template/CHANGELOG.md @@ -1,3 +1,9 @@ +## v1.4.1 (2026-04-08) + +### Bug Fixes +* Fix EFA field naming: `efa_interfaces` -> `efa`, `efa_interfaces_limit` -> `efa_limit` (#392) +* Fix deep health check nodeSelector label to `sagemaker.amazonaws.com/deep-health-check-status: Passed` for v1.0 and v1.1 (#386) + ## v1.4.0 (2026-01-27) ### Features diff --git a/hyperpod-pytorch-job-template/pyproject.toml b/hyperpod-pytorch-job-template/pyproject.toml index 20af842c..ec08bca3 100644 --- a/hyperpod-pytorch-job-template/pyproject.toml +++ b/hyperpod-pytorch-job-template/pyproject.toml @@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta" [project] name = "hyperpod-pytorch-job-template" -version = "1.4.0" +version = "1.4.1" readme = "README.md" authors = [{name = "Amazon Web Services"}] license = {text = "Apache-2.0"} diff --git a/pyproject.toml b/pyproject.toml index 3ef5206b..0be506d6 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta" [project] dynamic = ["dependencies"] name = "sagemaker-hyperpod" -version = "3.7.0" +version = "3.7.1" description = "Amazon SageMaker HyperPod SDK and CLI" readme = "README.md" requires-python = ">=3.8" diff --git a/setup.py b/setup.py index 49097c3f..b2449388 100644 --- a/setup.py +++ b/setup.py @@ -47,7 +47,7 @@ setup( data_files=sagemaker_hyperpod_recipes, name="sagemaker-hyperpod", - version="3.7.0", + version="3.7.1", description="Amazon SageMaker HyperPod SDK and CLI", long_description=open("README.md").read(), long_description_content_type="text/markdown",