feat: add InstancePools to EndpointConfig ProductionVariants - #362
Open
michaelhtm wants to merge 1 commit into
Open
feat: add InstancePools to EndpointConfig ProductionVariants#362michaelhtm wants to merge 1 commit into
michaelhtm wants to merge 1 commit into
Conversation
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: michaelhtm The full list of commands accepted by this bot can be found here. The pull request process is described here DetailsNeeds approval from an approver in each of these files:
Approvers can indicate their approval by writing |
michaelhtm
force-pushed
the
feat/add-instancepools-to-productionvariant
branch
from
July 16, 2026 19:44
87e3894 to
1bfb4e4
Compare
Member
Author
|
/label release/minor |
Bumps the sagemaker SDK to v1.244.0 to expose the InstancePools field on ProductionVariant, enabling heterogeneous endpoints that provision across a prioritized list of instance types. The field maps automatically as a nested field on the already-generated ProductionVariant shape; no hooks needed. The SDK bump also introduces unrelated new resources and fields. To keep the change scoped to InstancePools, new resources (AIBenchmarkJob, AIRecommendationJob, AIWorkloadConfig, MlflowApp, PresignedMlflowAppUrl) are added to ignore.resource_names, and new out-of-scope fields (MetricsConfig, Specifications, ScaleInPolicy, DataCacheConfig, SchedulingConfig, ModelPackageRegistrationType, AdditionalModelDataSources, BaseModel, DatasetSource, MlflowConfig, ModelPackageConfig, ServerlessJobConfig, VariantInstanceProvisionTimeoutInSeconds, MlflowExperimentName, and others) are added to ignore.field_paths on both their input and output shapes.
michaelhtm
force-pushed
the
feat/add-instancepools-to-productionvariant
branch
from
July 23, 2026 17:05
1bfb4e4 to
991342f
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description of changes:
Bumps the sagemaker SDK to v1.244.0 to expose the InstancePools field on
ProductionVariant, enabling heterogeneous endpoints that provision across a
prioritized list of instance types. The field maps automatically as a nested
field on the already-generated ProductionVariant shape; no hooks needed.
The SDK bump also introduces unrelated new resources and fields. To keep the
change scoped to InstancePools, new resources (AIBenchmarkJob,
AIRecommendationJob, AIWorkloadConfig, MlflowApp, PresignedMlflowAppUrl) are
added to ignore.resource_names, and new out-of-scope fields (MetricsConfig,
Specifications, ScaleInPolicy, DataCacheConfig, SchedulingConfig,
ModelPackageRegistrationType, AdditionalModelDataSources, BaseModel,
DatasetSource, MlflowConfig, ModelPackageConfig, ServerlessJobConfig,
VariantInstanceProvisionTimeoutInSeconds, MlflowExperimentName, and others)
are added to ignore.field_paths on both their input and output shapes.
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.