[Inference Operator] Update CRDs and Helm chart to v3.1#412

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
zicanl-amazon wants to merge 1 commit into
base:main
Choose a base branch
from
Open

[Inference Operator] Update CRDs and Helm chart to v3.1 #412

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -15,7 +15,7 @@ type: application
# This is the chart version. This version number should be incremented each time you make changes
# to the chart and its templates, including the app version.
# Versions are expected to follow Semantic Versioning (https://semver.org/)
version: 2.1.0
version: 2.2.0

# This is the version number of the application being deployed. Keep this aligned
# with operator image MAJOR.MINOR version.
Expand DownExpand Up@@ -50,4 +50,4 @@ dependencies:
alias: keda
version: 2.17.1
repository: "https://kedacore.github.io/charts"
condition: keda.enabled
condition: keda.enabled
307 changes: 302 additions & 5 deletions ...ence-operator/config/crd/inference.sagemaker.aws.amazon.com_inferenceendpointconfigs.yaml
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -270,7 +270,7 @@ spec:
type: string
serverAddress:
description: Server address for AMP workspace
pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
type: string
targetValue:
description: Target metric value for scaling
Expand DownExpand Up@@ -315,7 +315,7 @@ spec:
type: string
serverAddress:
description: Server address for AMP workspace
pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
type: string
targetValue:
description: Target metric value for scaling
Expand DownExpand Up@@ -343,6 +343,211 @@ spec:
minimum: 0
type: integer
type: object
dataCapture:
description: Configuration for data capture across multiple tiers
(SageMaker, LoadBalancer, Model Pod)
properties:
loadBalancer:
description: Configuration for LoadBalancer level data capture
(Tier 2)
properties:
enabled:
description: Enable or disable load balancer access logs
type: boolean
required:
- enabled
type: object
modelPod:
description: Configuration for Model Pod level data capture (Tier
3)
properties:
bufferConfig:
description: Configuration for buffering and flushing captured
data
properties:
batchSize:
default: 10
description: Number of records to batch before writing
to S3
format: int32
maximum: 1000
minimum: 1
type: integer
flushIntervalSeconds:
default: 60
description: Flush interval in seconds
format: int32
maximum: 300
minimum: 10
type: integer
type: object
captureContentTypeHeader:
description: Configuration for how to treat different content
type headers during capture
properties:
csvContentTypes:
description: |-
List of content type headers to treat as CSV
Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
Example: text/csv, application/csv
items:
type: string
maxItems: 10
minItems: 1
type: array
x-kubernetes-list-type: set
jsonContentTypes:
description: |-
List of content type headers to treat as JSON
Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
Example: application/json, application/jsonlines
items:
type: string
maxItems: 10
minItems: 1
type: array
x-kubernetes-list-type: set
type: object
captureOptions:
description: Capture options (Input, Output, or both). Defaults
to [Input, Output] when enabled.
items:
description: CaptureOption defines what data to capture
(input, output, or both).
properties:
captureMode:
description: 'Capture mode: Input or Output'
enum:
- Input
- Output
type: string
required:
- captureMode
type: object
maxItems: 32
minItems: 1
type: array
enabled:
description: Enable or disable model pod data capture
type: boolean
initialSamplingPercentage:
description: Percentage of requests to capture (0-100). Defaults
to 100 when enabled.
format: int32
maximum: 100
minimum: 0
type: integer
kmsKeyId:
description: Optional KMS key ID, ARN, alias name, or alias
ARN for encrypting captured data
maxLength: 2048
pattern: ^[a-zA-Z0-9:/_-]*$
type: string
payloadConfig:
description: Configuration for payload size limits
properties:
maxPayloadSizeKB:
default: 0
description: Maximum payload size in KB to capture. 0
means no limit (capture full payload).
format: int32
maximum: 10240
minimum: 0
type: integer
type: object
required:
- enabled
type: object
s3Uri:
description: |-
Common S3 URI for all data capture tiers. Each tier will write to a specific prefix within this bucket.
Must use s3:// protocol (required by ALB access logs).
If not provided, the TLS certificate bucket will be used for data capture storage.
maxLength: 512
pattern: ^s3://([^/]+)(/[^,=]*)?$
type: string
sagemakerEndpoint:
description: Configuration for SageMaker Endpoint level data capture
(Tier 1)
properties:
captureContentTypeHeader:
description: Configuration for how to treat different content
type headers during capture
properties:
csvContentTypes:
description: |-
List of content type headers to treat as CSV
Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
Example: text/csv, application/csv
items:
type: string
maxItems: 10
minItems: 1
type: array
x-kubernetes-list-type: set
jsonContentTypes:
description: |-
List of content type headers to treat as JSON
Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
Example: application/json, application/jsonlines
items:
type: string
maxItems: 10
minItems: 1
type: array
x-kubernetes-list-type: set
type: object
captureOptions:
description: Capture options (Input, Output, or both). Defaults
to [Input, Output] when enabled.
items:
description: CaptureOption defines what data to capture
(input, output, or both).
properties:
captureMode:
description: 'Capture mode: Input or Output'
enum:
- Input
- Output
type: string
required:
- captureMode
type: object
maxItems: 32
minItems: 1
type: array
enabled:
description: Enable or disable SageMaker endpoint data capture
type: boolean
initialSamplingPercentage:
description: Percentage of requests to capture (0-100). Defaults
to 100 when enabled.
format: int32
maximum: 100
minimum: 0
type: integer
kmsKeyId:
description: Optional KMS key ID, ARN, alias name, or alias
ARN for encrypting captured data
maxLength: 2048
pattern: ^[a-zA-Z0-9:/_-]*$
type: string
required:
- enabled
type: object
type: object
dnsConfig:
description: DNS automation configuration for Route53. Requires tlsConfig.customCertificateConfig
to be set.
properties:
hostedZoneId:
description: Route53 Hosted Zone ID where the DNS record will
be created.
pattern: ^Z[A-Z0-9]+$
type: string
required:
- hostedZoneId
type: object
endpointName:
description: |-
Name used for Sagemaker Endpoint
Expand DownExpand Up@@ -589,7 +794,7 @@ spec:
type: string
serverAddress:
description: Server address for AMP workspace
pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
type: string
targetValue:
description: Target metric value for scaling
Expand DownExpand Up@@ -636,7 +841,7 @@ spec:
type: string
serverAddress:
description: Server address for AMP workspace
pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
type: string
targetValue:
description: Target metric value for scaling
Expand DownExpand Up@@ -2230,6 +2435,14 @@ spec:
maxLength: 253
pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$
type: string
serviceAccountName:
description: |-
Name of the Kubernetes ServiceAccount to use for the inference pod.
If not specified, the namespace's default service account will be used.
This is useful for providing AWS credentials via IRSA to init containers or the worker.
maxLength: 253
pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$
type: string
volumes:
description: |-
Additional volumes to add to the pod spec.
Expand DownExpand Up@@ -4249,13 +4462,59 @@ spec:
required:
- fileSystemId
type: object
huggingFaceModel:
description: HuggingFace model configuration. Required when modelSourceType
is "huggingface".
properties:
commitSHA:
description: |-
Git commit SHA for the model revision. Must be a full 40-character lowercase hex SHA.
If not provided, the operator defaults to "main" branch.
pattern: ^[0-9a-f]{40}$
type: string
modelId:
description: HuggingFace Hub model identifier in org/model
format (e.g. "meta-llama/Llama-3.1-8B-Instruct").
pattern: ^[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+$
type: string
tokenSecretRef:
description: |-
Reference to a Kubernetes Secret containing the HuggingFace API token.
The token is injected as the HF_TOKEN environment variable into the InitContainer only.
properties:
key:
description: The key of the secret to select from. Must
be a valid secret key.
type: string
name:
default: ""
description: |-
Name of the referent.
This field is effectively required, but due to backwards compatibility is
allowed to be empty. Instances of this type with an empty value here are
almost certainly wrong.
More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
type: string
optional:
description: Specify whether the Secret or its key must
be defined
type: boolean
required:
- key
type: object
x-kubernetes-map-type: atomic
required:
- modelId
type: object
modelLocation:
description: Specific location where the model data exists
type: string
modelSourceType:
enum:
- fsx
- s3
- huggingface
- kubernetesVolume
type: string
prefetchEnabled:
default: false
Expand DownExpand Up@@ -5492,6 +5751,44 @@ spec:
- lastUpdated
- name
type: object
dnsStatus:
description: Status of the operator-managed Route53 DNS record
properties:
dnsHealth:
description: 'DNS resolution status: Active, Pending, or Error.'
enum:
- Active
- Pending
- Error
type: string
hostedZoneId:
description: Route53 hosted zone ID.
type: string
lastTransitionTime:
description: When the status last transitioned, used for propagation
timeout.
format: date-time
type: string
managedByOperator:
description: Whether the operator manages this DNS record.
type: boolean
message:
description: Human-readable status or error message.
type: string
previousHostedZoneId:
description: Previous hosted zone ID, retained during domain/zone
changes until cleanup completes.
type: string
previousRecordName:
description: Previous record name, retained during domain/zone
changes until cleanup completes.
type: string
recordName:
description: Route53 record name.
type: string
required:
- managedByOperator
type: object
endpoints:
description: EndpointStatus contains the status of SageMaker endpoints
properties:
Expand DownExpand Up@@ -5801,7 +6098,7 @@ spec:
type: string
serverAddress:
description: Server address for AMP workspace
pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
type: string
targetValue:
description: Target metric value for scaling
Expand Down
Loading
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { // Add copy buttons to all 
 blocks
(function() {
function addCopyButtons() {
document.querySelectorAll('pre code').forEach(function(codeBlock) {
if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;
codeBlock.parentElement.setAttribute('data-copy-added', 'true');
var btn = document.createElement('button');
btn.textContent = 'Copy';
btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';
btn.onmouseover = function() { this.style.opacity = '1'; };
btn.onmouseout = function() { this.style.opacity = '0.7'; };
btn.onclick = function() {
navigator.clipboard.writeText(codeBlock.textContent).then(function() {
btn.textContent = 'Copied!';
setTimeout(function() { btn.textContent = 'Copy'; }, 1500);
});
};
codeBlock.parentElement.style.position = 'relative';
codeBlock.parentElement.appendChild(btn);
});
}
addCopyButtons();
// Re-run on dynamic content
var observer = new MutationObserver(addCopyButtons);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
[Inference Operator] Update CRDs and Helm chart to v3.1#412

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Open

zicanl-amazon
wants to merge
1
commit into

base:main
Choose a base branch

from

 Open


[Inference Operator] Update CRDs and Helm chart to v3.1
#412
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


4 changes: 2 additions & 2 deletions
helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -15,7 +15,7 @@ type: application
# This is the chart version. This version number should be incremented each time you make changes
# to the chart and its templates, including the app version.
# Versions are expected to follow Semantic Versioning (https://semver.org/)
version: 2.1.0
version: 2.2.0

# This is the version number of the application being deployed. Keep this aligned 
# with operator image MAJOR.MINOR version.
Expand DownExpand Up@@ -50,4 +50,4 @@ dependencies:
 alias: keda
 version: 2.17.1
 repository: "https://kedacore.github.io/charts"
 condition: keda.enabled
 condition: keda.enabled

307 changes: 302 additions & 5 deletions
...ence-operator/config/crd/inference.sagemaker.aws.amazon.com_inferenceendpointconfigs.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -270,7 +270,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -315,7 +315,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -343,6 +343,211 @@ spec:
 minimum: 0
 type: integer
 type: object
 dataCapture:
 description: Configuration for data capture across multiple tiers
 (SageMaker, LoadBalancer, Model Pod)
 properties:
 loadBalancer:
 description: Configuration for LoadBalancer level data capture
 (Tier 2)
 properties:
 enabled:
 description: Enable or disable load balancer access logs
 type: boolean
 required:
 - enabled
 type: object
 modelPod:
 description: Configuration for Model Pod level data capture (Tier
 3)
 properties:
 bufferConfig:
 description: Configuration for buffering and flushing captured
 data
 properties:
 batchSize:
 default: 10
 description: Number of records to batch before writing
 to S3
 format: int32
 maximum: 1000
 minimum: 1
 type: integer
 flushIntervalSeconds:
 default: 60
 description: Flush interval in seconds
 format: int32
 maximum: 300
 minimum: 10
 type: integer
 type: object
 captureContentTypeHeader:
 description: Configuration for how to treat different content
 type headers during capture
 properties:
 csvContentTypes:
 description: |-
 List of content type headers to treat as CSV
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: text/csv, application/csv
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 jsonContentTypes:
 description: |-
 List of content type headers to treat as JSON
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: application/json, application/jsonlines
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 type: object
 captureOptions:
 description: Capture options (Input, Output, or both). Defaults
 to [Input, Output] when enabled.
 items:
 description: CaptureOption defines what data to capture
 (input, output, or both).
 properties:
 captureMode:
 description: 'Capture mode: Input or Output'
 enum:
 - Input
 - Output
 type: string
 required:
 - captureMode
 type: object
 maxItems: 32
 minItems: 1
 type: array
 enabled:
 description: Enable or disable model pod data capture
 type: boolean
 initialSamplingPercentage:
 description: Percentage of requests to capture (0-100). Defaults
 to 100 when enabled.
 format: int32
 maximum: 100
 minimum: 0
 type: integer
 kmsKeyId:
 description: Optional KMS key ID, ARN, alias name, or alias
 ARN for encrypting captured data
 maxLength: 2048
 pattern: ^[a-zA-Z0-9:/_-]*$
 type: string
 payloadConfig:
 description: Configuration for payload size limits
 properties:
 maxPayloadSizeKB:
 default: 0
 description: Maximum payload size in KB to capture. 0
 means no limit (capture full payload).
 format: int32
 maximum: 10240
 minimum: 0
 type: integer
 type: object
 required:
 - enabled
 type: object
 s3Uri:
 description: |-
 Common S3 URI for all data capture tiers. Each tier will write to a specific prefix within this bucket.
 Must use s3:// protocol (required by ALB access logs).
 If not provided, the TLS certificate bucket will be used for data capture storage.
 maxLength: 512
 pattern: ^s3://([^/]+)(/[^,=]*)?$
 type: string
 sagemakerEndpoint:
 description: Configuration for SageMaker Endpoint level data capture
 (Tier 1)
 properties:
 captureContentTypeHeader:
 description: Configuration for how to treat different content
 type headers during capture
 properties:
 csvContentTypes:
 description: |-
 List of content type headers to treat as CSV
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: text/csv, application/csv
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 jsonContentTypes:
 description: |-
 List of content type headers to treat as JSON
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: application/json, application/jsonlines
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 type: object
 captureOptions:
 description: Capture options (Input, Output, or both). Defaults
 to [Input, Output] when enabled.
 items:
 description: CaptureOption defines what data to capture
 (input, output, or both).
 properties:
 captureMode:
 description: 'Capture mode: Input or Output'
 enum:
 - Input
 - Output
 type: string
 required:
 - captureMode
 type: object
 maxItems: 32
 minItems: 1
 type: array
 enabled:
 description: Enable or disable SageMaker endpoint data capture
 type: boolean
 initialSamplingPercentage:
 description: Percentage of requests to capture (0-100). Defaults
 to 100 when enabled.
 format: int32
 maximum: 100
 minimum: 0
 type: integer
 kmsKeyId:
 description: Optional KMS key ID, ARN, alias name, or alias
 ARN for encrypting captured data
 maxLength: 2048
 pattern: ^[a-zA-Z0-9:/_-]*$
 type: string
 required:
 - enabled
 type: object
 type: object
 dnsConfig:
 description: DNS automation configuration for Route53. Requires tlsConfig.customCertificateConfig
 to be set.
 properties:
 hostedZoneId:
 description: Route53 Hosted Zone ID where the DNS record will
 be created.
 pattern: ^Z[A-Z0-9]+$
 type: string
 required:
 - hostedZoneId
 type: object
 endpointName:
 description: |-
 Name used for Sagemaker Endpoint
Expand DownExpand Up@@ -589,7 +794,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -636,7 +841,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -2230,6 +2435,14 @@ spec:
 maxLength: 253
 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$
 type: string
 serviceAccountName:
 description: |-
 Name of the Kubernetes ServiceAccount to use for the inference pod.
 If not specified, the namespace's default service account will be used.
 This is useful for providing AWS credentials via IRSA to init containers or the worker.
 maxLength: 253
 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$
 type: string
 volumes:
 description: |-
 Additional volumes to add to the pod spec.
Expand DownExpand Up@@ -4249,13 +4462,59 @@ spec:
 required:
 - fileSystemId
 type: object
 huggingFaceModel:
 description: HuggingFace model configuration. Required when modelSourceType
 is "huggingface".
 properties:
 commitSHA:
 description: |-
 Git commit SHA for the model revision. Must be a full 40-character lowercase hex SHA.
 If not provided, the operator defaults to "main" branch.
 pattern: ^[0-9a-f]{40}$
 type: string
 modelId:
 description: HuggingFace Hub model identifier in org/model
 format (e.g. "meta-llama/Llama-3.1-8B-Instruct").
 pattern: ^[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+$
 type: string
 tokenSecretRef:
 description: |-
 Reference to a Kubernetes Secret containing the HuggingFace API token.
 The token is injected as the HF_TOKEN environment variable into the InitContainer only.
 properties:
 key:
 description: The key of the secret to select from. Must
 be a valid secret key.
 type: string
 name:
 default: ""
 description: |-
 Name of the referent.
 This field is effectively required, but due to backwards compatibility is
 allowed to be empty. Instances of this type with an empty value here are
 almost certainly wrong.
 More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
 type: string
 optional:
 description: Specify whether the Secret or its key must
 be defined
 type: boolean
 required:
 - key
 type: object
 x-kubernetes-map-type: atomic
 required:
 - modelId
 type: object
 modelLocation:
 description: Specific location where the model data exists
 type: string
 modelSourceType:
 enum:
 - fsx
 - s3
 - huggingface
 - kubernetesVolume
 type: string
 prefetchEnabled:
 default: false
Expand DownExpand Up@@ -5492,6 +5751,44 @@ spec:
 - lastUpdated
 - name
 type: object
 dnsStatus:
 description: Status of the operator-managed Route53 DNS record
 properties:
 dnsHealth:
 description: 'DNS resolution status: Active, Pending, or Error.'
 enum:
 - Active
 - Pending
 - Error
 type: string
 hostedZoneId:
 description: Route53 hosted zone ID.
 type: string
 lastTransitionTime:
 description: When the status last transitioned, used for propagation
 timeout.
 format: date-time
 type: string
 managedByOperator:
 description: Whether the operator manages this DNS record.
 type: boolean
 message:
 description: Human-readable status or error message.
 type: string
 previousHostedZoneId:
 description: Previous hosted zone ID, retained during domain/zone
 changes until cleanup completes.
 type: string
 previousRecordName:
 description: Previous record name, retained during domain/zone
 changes until cleanup completes.
 type: string
 recordName:
 description: Route53 record name.
 type: string
 required:
 - managedByOperator
 type: object
 endpoints:
 description: EndpointStatus contains the status of SageMaker endpoints
 properties:
Expand DownExpand Up@@ -5801,7 +6098,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand Down
Loading
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Force GitHub README to respect dark mode
(function() {
var style = document.createElement('style');
style.textContent = '
.markdown-body {
color-scheme: dark light;
}
.markdown-body pre { background: #161b22 !important; }
.markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }
.markdown-body table th, .markdown-body table td { border-color: #30363d !important; }
.markdown-body img { background: #0d1117; }
.markdown-body blockquote { border-left-color: #8b949e; }
.markdown-body hr { border-color: #30363d; }
';
document.head.appendChild(style);
})();
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
[Inference Operator] Update CRDs and Helm chart to v3.1#412

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Open

zicanl-amazon
wants to merge
1
commit into

base:main
Choose a base branch

from

 Open


[Inference Operator] Update CRDs and Helm chart to v3.1
#412
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


4 changes: 2 additions & 2 deletions
helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -15,7 +15,7 @@ type: application
# This is the chart version. This version number should be incremented each time you make changes
# to the chart and its templates, including the app version.
# Versions are expected to follow Semantic Versioning (https://semver.org/)
version: 2.1.0
version: 2.2.0

# This is the version number of the application being deployed. Keep this aligned 
# with operator image MAJOR.MINOR version.
Expand DownExpand Up@@ -50,4 +50,4 @@ dependencies:
 alias: keda
 version: 2.17.1
 repository: "https://kedacore.github.io/charts"
 condition: keda.enabled
 condition: keda.enabled

307 changes: 302 additions & 5 deletions
...ence-operator/config/crd/inference.sagemaker.aws.amazon.com_inferenceendpointconfigs.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -270,7 +270,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -315,7 +315,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -343,6 +343,211 @@ spec:
 minimum: 0
 type: integer
 type: object
 dataCapture:
 description: Configuration for data capture across multiple tiers
 (SageMaker, LoadBalancer, Model Pod)
 properties:
 loadBalancer:
 description: Configuration for LoadBalancer level data capture
 (Tier 2)
 properties:
 enabled:
 description: Enable or disable load balancer access logs
 type: boolean
 required:
 - enabled
 type: object
 modelPod:
 description: Configuration for Model Pod level data capture (Tier
 3)
 properties:
 bufferConfig:
 description: Configuration for buffering and flushing captured
 data
 properties:
 batchSize:
 default: 10
 description: Number of records to batch before writing
 to S3
 format: int32
 maximum: 1000
 minimum: 1
 type: integer
 flushIntervalSeconds:
 default: 60
 description: Flush interval in seconds
 format: int32
 maximum: 300
 minimum: 10
 type: integer
 type: object
 captureContentTypeHeader:
 description: Configuration for how to treat different content
 type headers during capture
 properties:
 csvContentTypes:
 description: |-
 List of content type headers to treat as CSV
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: text/csv, application/csv
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 jsonContentTypes:
 description: |-
 List of content type headers to treat as JSON
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: application/json, application/jsonlines
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 type: object
 captureOptions:
 description: Capture options (Input, Output, or both). Defaults
 to [Input, Output] when enabled.
 items:
 description: CaptureOption defines what data to capture
 (input, output, or both).
 properties:
 captureMode:
 description: 'Capture mode: Input or Output'
 enum:
 - Input
 - Output
 type: string
 required:
 - captureMode
 type: object
 maxItems: 32
 minItems: 1
 type: array
 enabled:
 description: Enable or disable model pod data capture
 type: boolean
 initialSamplingPercentage:
 description: Percentage of requests to capture (0-100). Defaults
 to 100 when enabled.
 format: int32
 maximum: 100
 minimum: 0
 type: integer
 kmsKeyId:
 description: Optional KMS key ID, ARN, alias name, or alias
 ARN for encrypting captured data
 maxLength: 2048
 pattern: ^[a-zA-Z0-9:/_-]*$
 type: string
 payloadConfig:
 description: Configuration for payload size limits
 properties:
 maxPayloadSizeKB:
 default: 0
 description: Maximum payload size in KB to capture. 0
 means no limit (capture full payload).
 format: int32
 maximum: 10240
 minimum: 0
 type: integer
 type: object
 required:
 - enabled
 type: object
 s3Uri:
 description: |-
 Common S3 URI for all data capture tiers. Each tier will write to a specific prefix within this bucket.
 Must use s3:// protocol (required by ALB access logs).
 If not provided, the TLS certificate bucket will be used for data capture storage.
 maxLength: 512
 pattern: ^s3://([^/]+)(/[^,=]*)?$
 type: string
 sagemakerEndpoint:
 description: Configuration for SageMaker Endpoint level data capture
 (Tier 1)
 properties:
 captureContentTypeHeader:
 description: Configuration for how to treat different content
 type headers during capture
 properties:
 csvContentTypes:
 description: |-
 List of content type headers to treat as CSV
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: text/csv, application/csv
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 jsonContentTypes:
 description: |-
 List of content type headers to treat as JSON
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: application/json, application/jsonlines
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 type: object
 captureOptions:
 description: Capture options (Input, Output, or both). Defaults
 to [Input, Output] when enabled.
 items:
 description: CaptureOption defines what data to capture
 (input, output, or both).
 properties:
 captureMode:
 description: 'Capture mode: Input or Output'
 enum:
 - Input
 - Output
 type: string
 required:
 - captureMode
 type: object
 maxItems: 32
 minItems: 1
 type: array
 enabled:
 description: Enable or disable SageMaker endpoint data capture
 type: boolean
 initialSamplingPercentage:
 description: Percentage of requests to capture (0-100). Defaults
 to 100 when enabled.
 format: int32
 maximum: 100
 minimum: 0
 type: integer
 kmsKeyId:
 description: Optional KMS key ID, ARN, alias name, or alias
 ARN for encrypting captured data
 maxLength: 2048
 pattern: ^[a-zA-Z0-9:/_-]*$
 type: string
 required:
 - enabled
 type: object
 type: object
 dnsConfig:
 description: DNS automation configuration for Route53. Requires tlsConfig.customCertificateConfig
 to be set.
 properties:
 hostedZoneId:
 description: Route53 Hosted Zone ID where the DNS record will
 be created.
 pattern: ^Z[A-Z0-9]+$
 type: string
 required:
 - hostedZoneId
 type: object
 endpointName:
 description: |-
 Name used for Sagemaker Endpoint
Expand DownExpand Up@@ -589,7 +794,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -636,7 +841,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -2230,6 +2435,14 @@ spec:
 maxLength: 253
 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$
 type: string
 serviceAccountName:
 description: |-
 Name of the Kubernetes ServiceAccount to use for the inference pod.
 If not specified, the namespace's default service account will be used.
 This is useful for providing AWS credentials via IRSA to init containers or the worker.
 maxLength: 253
 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$
 type: string
 volumes:
 description: |-
 Additional volumes to add to the pod spec.
Expand DownExpand Up@@ -4249,13 +4462,59 @@ spec:
 required:
 - fileSystemId
 type: object
 huggingFaceModel:
 description: HuggingFace model configuration. Required when modelSourceType
 is "huggingface".
 properties:
 commitSHA:
 description: |-
 Git commit SHA for the model revision. Must be a full 40-character lowercase hex SHA.
 If not provided, the operator defaults to "main" branch.
 pattern: ^[0-9a-f]{40}$
 type: string
 modelId:
 description: HuggingFace Hub model identifier in org/model
 format (e.g. "meta-llama/Llama-3.1-8B-Instruct").
 pattern: ^[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+$
 type: string
 tokenSecretRef:
 description: |-
 Reference to a Kubernetes Secret containing the HuggingFace API token.
 The token is injected as the HF_TOKEN environment variable into the InitContainer only.
 properties:
 key:
 description: The key of the secret to select from. Must
 be a valid secret key.
 type: string
 name:
 default: ""
 description: |-
 Name of the referent.
 This field is effectively required, but due to backwards compatibility is
 allowed to be empty. Instances of this type with an empty value here are
 almost certainly wrong.
 More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
 type: string
 optional:
 description: Specify whether the Secret or its key must
 be defined
 type: boolean
 required:
 - key
 type: object
 x-kubernetes-map-type: atomic
 required:
 - modelId
 type: object
 modelLocation:
 description: Specific location where the model data exists
 type: string
 modelSourceType:
 enum:
 - fsx
 - s3
 - huggingface
 - kubernetesVolume
 type: string
 prefetchEnabled:
 default: false
Expand DownExpand Up@@ -5492,6 +5751,44 @@ spec:
 - lastUpdated
 - name
 type: object
 dnsStatus:
 description: Status of the operator-managed Route53 DNS record
 properties:
 dnsHealth:
 description: 'DNS resolution status: Active, Pending, or Error.'
 enum:
 - Active
 - Pending
 - Error
 type: string
 hostedZoneId:
 description: Route53 hosted zone ID.
 type: string
 lastTransitionTime:
 description: When the status last transitioned, used for propagation
 timeout.
 format: date-time
 type: string
 managedByOperator:
 description: Whether the operator manages this DNS record.
 type: boolean
 message:
 description: Human-readable status or error message.
 type: string
 previousHostedZoneId:
 description: Previous hosted zone ID, retained during domain/zone
 changes until cleanup completes.
 type: string
 previousRecordName:
 description: Previous record name, retained during domain/zone
 changes until cleanup completes.
 type: string
 recordName:
 description: Route53 record name.
 type: string
 required:
 - managedByOperator
 type: object
 endpoints:
 description: EndpointStatus contains the status of SageMaker endpoints
 properties:
Expand DownExpand Up@@ -5801,7 +6098,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand Down
Loading
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Highlight search terms from Google/DuckDuckGo/Bing referrer
(function() {
var ref = document.referrer;
var terms = [];
if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {
var url = new URL(ref);
var q = url.searchParams.get('q') || url.searchParams.get('p');
if (q) {
terms = q.split(/\s+/).filter(function(t) { return t.length > 2; });
}
}
if (terms.length === 0) return;
var style = document.createElement('style');
style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';
document.head.appendChild(style);
function highlight(node) {
if (node.nodeType === 3) { // text node
var text = node.textContent;
var found = false;
terms.forEach(function(term) {
var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\]\\]/g, '\\') + ')', 'gi');
if (regex.test(text)) {
found = true;
var frag = document.createDocumentFragment();
var parts = text.split(regex);
parts.forEach(function(part, i) {
if (i % 2 === 0) {
frag.appendChild(document.createTextNode(part));
} else {
var span = document.createElement('span');
span.className = 'userscript-highlight';
span.textContent = part;
frag.appendChild(span);
}
});
node.parentNode.replaceChild(frag, node);
}
});
} else if (node.nodeType === 1 && node.childNodes) { // element
var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];
if (!skipTags.includes(node.tagName)) {
Array.from(node.childNodes).forEach(highlight);
}
}
}
highlight(document.body);
// Re-highlight on dynamic content
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1 || node.nodeType === 3) highlight(node);
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
[Inference Operator] Update CRDs and Helm chart to v3.1#412

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Open

zicanl-amazon
wants to merge
1
commit into

base:main
Choose a base branch

from

 Open


[Inference Operator] Update CRDs and Helm chart to v3.1
#412
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


4 changes: 2 additions & 2 deletions
helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -15,7 +15,7 @@ type: application
# This is the chart version. This version number should be incremented each time you make changes
# to the chart and its templates, including the app version.
# Versions are expected to follow Semantic Versioning (https://semver.org/)
version: 2.1.0
version: 2.2.0

# This is the version number of the application being deployed. Keep this aligned 
# with operator image MAJOR.MINOR version.
Expand DownExpand Up@@ -50,4 +50,4 @@ dependencies:
 alias: keda
 version: 2.17.1
 repository: "https://kedacore.github.io/charts"
 condition: keda.enabled
 condition: keda.enabled

307 changes: 302 additions & 5 deletions
...ence-operator/config/crd/inference.sagemaker.aws.amazon.com_inferenceendpointconfigs.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -270,7 +270,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -315,7 +315,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -343,6 +343,211 @@ spec:
 minimum: 0
 type: integer
 type: object
 dataCapture:
 description: Configuration for data capture across multiple tiers
 (SageMaker, LoadBalancer, Model Pod)
 properties:
 loadBalancer:
 description: Configuration for LoadBalancer level data capture
 (Tier 2)
 properties:
 enabled:
 description: Enable or disable load balancer access logs
 type: boolean
 required:
 - enabled
 type: object
 modelPod:
 description: Configuration for Model Pod level data capture (Tier
 3)
 properties:
 bufferConfig:
 description: Configuration for buffering and flushing captured
 data
 properties:
 batchSize:
 default: 10
 description: Number of records to batch before writing
 to S3
 format: int32
 maximum: 1000
 minimum: 1
 type: integer
 flushIntervalSeconds:
 default: 60
 description: Flush interval in seconds
 format: int32
 maximum: 300
 minimum: 10
 type: integer
 type: object
 captureContentTypeHeader:
 description: Configuration for how to treat different content
 type headers during capture
 properties:
 csvContentTypes:
 description: |-
 List of content type headers to treat as CSV
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: text/csv, application/csv
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 jsonContentTypes:
 description: |-
 List of content type headers to treat as JSON
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: application/json, application/jsonlines
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 type: object
 captureOptions:
 description: Capture options (Input, Output, or both). Defaults
 to [Input, Output] when enabled.
 items:
 description: CaptureOption defines what data to capture
 (input, output, or both).
 properties:
 captureMode:
 description: 'Capture mode: Input or Output'
 enum:
 - Input
 - Output
 type: string
 required:
 - captureMode
 type: object
 maxItems: 32
 minItems: 1
 type: array
 enabled:
 description: Enable or disable model pod data capture
 type: boolean
 initialSamplingPercentage:
 description: Percentage of requests to capture (0-100). Defaults
 to 100 when enabled.
 format: int32
 maximum: 100
 minimum: 0
 type: integer
 kmsKeyId:
 description: Optional KMS key ID, ARN, alias name, or alias
 ARN for encrypting captured data
 maxLength: 2048
 pattern: ^[a-zA-Z0-9:/_-]*$
 type: string
 payloadConfig:
 description: Configuration for payload size limits
 properties:
 maxPayloadSizeKB:
 default: 0
 description: Maximum payload size in KB to capture. 0
 means no limit (capture full payload).
 format: int32
 maximum: 10240
 minimum: 0
 type: integer
 type: object
 required:
 - enabled
 type: object
 s3Uri:
 description: |-
 Common S3 URI for all data capture tiers. Each tier will write to a specific prefix within this bucket.
 Must use s3:// protocol (required by ALB access logs).
 If not provided, the TLS certificate bucket will be used for data capture storage.
 maxLength: 512
 pattern: ^s3://([^/]+)(/[^,=]*)?$
 type: string
 sagemakerEndpoint:
 description: Configuration for SageMaker Endpoint level data capture
 (Tier 1)
 properties:
 captureContentTypeHeader:
 description: Configuration for how to treat different content
 type headers during capture
 properties:
 csvContentTypes:
 description: |-
 List of content type headers to treat as CSV
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: text/csv, application/csv
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 jsonContentTypes:
 description: |-
 List of content type headers to treat as JSON
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: application/json, application/jsonlines
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 type: object
 captureOptions:
 description: Capture options (Input, Output, or both). Defaults
 to [Input, Output] when enabled.
 items:
 description: CaptureOption defines what data to capture
 (input, output, or both).
 properties:
 captureMode:
 description: 'Capture mode: Input or Output'
 enum:
 - Input
 - Output
 type: string
 required:
 - captureMode
 type: object
 maxItems: 32
 minItems: 1
 type: array
 enabled:
 description: Enable or disable SageMaker endpoint data capture
 type: boolean
 initialSamplingPercentage:
 description: Percentage of requests to capture (0-100). Defaults
 to 100 when enabled.
 format: int32
 maximum: 100
 minimum: 0
 type: integer
 kmsKeyId:
 description: Optional KMS key ID, ARN, alias name, or alias
 ARN for encrypting captured data
 maxLength: 2048
 pattern: ^[a-zA-Z0-9:/_-]*$
 type: string
 required:
 - enabled
 type: object
 type: object
 dnsConfig:
 description: DNS automation configuration for Route53. Requires tlsConfig.customCertificateConfig
 to be set.
 properties:
 hostedZoneId:
 description: Route53 Hosted Zone ID where the DNS record will
 be created.
 pattern: ^Z[A-Z0-9]+$
 type: string
 required:
 - hostedZoneId
 type: object
 endpointName:
 description: |-
 Name used for Sagemaker Endpoint
Expand DownExpand Up@@ -589,7 +794,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -636,7 +841,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -2230,6 +2435,14 @@ spec:
 maxLength: 253
 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$
 type: string
 serviceAccountName:
 description: |-
 Name of the Kubernetes ServiceAccount to use for the inference pod.
 If not specified, the namespace's default service account will be used.
 This is useful for providing AWS credentials via IRSA to init containers or the worker.
 maxLength: 253
 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$
 type: string
 volumes:
 description: |-
 Additional volumes to add to the pod spec.
Expand DownExpand Up@@ -4249,13 +4462,59 @@ spec:
 required:
 - fileSystemId
 type: object
 huggingFaceModel:
 description: HuggingFace model configuration. Required when modelSourceType
 is "huggingface".
 properties:
 commitSHA:
 description: |-
 Git commit SHA for the model revision. Must be a full 40-character lowercase hex SHA.
 If not provided, the operator defaults to "main" branch.
 pattern: ^[0-9a-f]{40}$
 type: string
 modelId:
 description: HuggingFace Hub model identifier in org/model
 format (e.g. "meta-llama/Llama-3.1-8B-Instruct").
 pattern: ^[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+$
 type: string
 tokenSecretRef:
 description: |-
 Reference to a Kubernetes Secret containing the HuggingFace API token.
 The token is injected as the HF_TOKEN environment variable into the InitContainer only.
 properties:
 key:
 description: The key of the secret to select from. Must
 be a valid secret key.
 type: string
 name:
 default: ""
 description: |-
 Name of the referent.
 This field is effectively required, but due to backwards compatibility is
 allowed to be empty. Instances of this type with an empty value here are
 almost certainly wrong.
 More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
 type: string
 optional:
 description: Specify whether the Secret or its key must
 be defined
 type: boolean
 required:
 - key
 type: object
 x-kubernetes-map-type: atomic
 required:
 - modelId
 type: object
 modelLocation:
 description: Specific location where the model data exists
 type: string
 modelSourceType:
 enum:
 - fsx
 - s3
 - huggingface
 - kubernetesVolume
 type: string
 prefetchEnabled:
 default: false
Expand DownExpand Up@@ -5492,6 +5751,44 @@ spec:
 - lastUpdated
 - name
 type: object
 dnsStatus:
 description: Status of the operator-managed Route53 DNS record
 properties:
 dnsHealth:
 description: 'DNS resolution status: Active, Pending, or Error.'
 enum:
 - Active
 - Pending
 - Error
 type: string
 hostedZoneId:
 description: Route53 hosted zone ID.
 type: string
 lastTransitionTime:
 description: When the status last transitioned, used for propagation
 timeout.
 format: date-time
 type: string
 managedByOperator:
 description: Whether the operator manages this DNS record.
 type: boolean
 message:
 description: Human-readable status or error message.
 type: string
 previousHostedZoneId:
 description: Previous hosted zone ID, retained during domain/zone
 changes until cleanup completes.
 type: string
 previousRecordName:
 description: Previous record name, retained during domain/zone
 changes until cleanup completes.
 type: string
 recordName:
 description: Route53 record name.
 type: string
 required:
 - managedByOperator
 type: object
 endpoints:
 description: EndpointStatus contains the status of SageMaker endpoints
 properties:
Expand DownExpand Up@@ -5801,7 +6098,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand Down
Loading
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Strip utm_, fbclid, gclid, etc. from all links on page
(function() {
var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',
'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',
'ref', 'ref_src', 'source', 'medium', 'campaign'];
function cleanUrl(url) {
try {
var u = new URL(url, window.location.origin);
var changed = false;
trackingParams.forEach(function(p) {
if (u.searchParams.has(p)) {
u.searchParams.delete(p);
changed = true;
}
});
return changed ? u.toString() : url;
} catch (e) {
return url;
}
}
function cleanLinks() {
document.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
cleanLinks();
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1) {
if (node.tagName === 'A') cleanLinks();
node.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
[Inference Operator] Update CRDs and Helm chart to v3.1#412

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Open

zicanl-amazon
wants to merge
1
commit into

base:main
Choose a base branch

from

 Open


[Inference Operator] Update CRDs and Helm chart to v3.1
#412
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


4 changes: 2 additions & 2 deletions
helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -15,7 +15,7 @@ type: application
# This is the chart version. This version number should be incremented each time you make changes
# to the chart and its templates, including the app version.
# Versions are expected to follow Semantic Versioning (https://semver.org/)
version: 2.1.0
version: 2.2.0

# This is the version number of the application being deployed. Keep this aligned 
# with operator image MAJOR.MINOR version.
Expand DownExpand Up@@ -50,4 +50,4 @@ dependencies:
 alias: keda
 version: 2.17.1
 repository: "https://kedacore.github.io/charts"
 condition: keda.enabled
 condition: keda.enabled

307 changes: 302 additions & 5 deletions
...ence-operator/config/crd/inference.sagemaker.aws.amazon.com_inferenceendpointconfigs.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -270,7 +270,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -315,7 +315,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -343,6 +343,211 @@ spec:
 minimum: 0
 type: integer
 type: object
 dataCapture:
 description: Configuration for data capture across multiple tiers
 (SageMaker, LoadBalancer, Model Pod)
 properties:
 loadBalancer:
 description: Configuration for LoadBalancer level data capture
 (Tier 2)
 properties:
 enabled:
 description: Enable or disable load balancer access logs
 type: boolean
 required:
 - enabled
 type: object
 modelPod:
 description: Configuration for Model Pod level data capture (Tier
 3)
 properties:
 bufferConfig:
 description: Configuration for buffering and flushing captured
 data
 properties:
 batchSize:
 default: 10
 description: Number of records to batch before writing
 to S3
 format: int32
 maximum: 1000
 minimum: 1
 type: integer
 flushIntervalSeconds:
 default: 60
 description: Flush interval in seconds
 format: int32
 maximum: 300
 minimum: 10
 type: integer
 type: object
 captureContentTypeHeader:
 description: Configuration for how to treat different content
 type headers during capture
 properties:
 csvContentTypes:
 description: |-
 List of content type headers to treat as CSV
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: text/csv, application/csv
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 jsonContentTypes:
 description: |-
 List of content type headers to treat as JSON
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: application/json, application/jsonlines
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 type: object
 captureOptions:
 description: Capture options (Input, Output, or both). Defaults
 to [Input, Output] when enabled.
 items:
 description: CaptureOption defines what data to capture
 (input, output, or both).
 properties:
 captureMode:
 description: 'Capture mode: Input or Output'
 enum:
 - Input
 - Output
 type: string
 required:
 - captureMode
 type: object
 maxItems: 32
 minItems: 1
 type: array
 enabled:
 description: Enable or disable model pod data capture
 type: boolean
 initialSamplingPercentage:
 description: Percentage of requests to capture (0-100). Defaults
 to 100 when enabled.
 format: int32
 maximum: 100
 minimum: 0
 type: integer
 kmsKeyId:
 description: Optional KMS key ID, ARN, alias name, or alias
 ARN for encrypting captured data
 maxLength: 2048
 pattern: ^[a-zA-Z0-9:/_-]*$
 type: string
 payloadConfig:
 description: Configuration for payload size limits
 properties:
 maxPayloadSizeKB:
 default: 0
 description: Maximum payload size in KB to capture. 0
 means no limit (capture full payload).
 format: int32
 maximum: 10240
 minimum: 0
 type: integer
 type: object
 required:
 - enabled
 type: object
 s3Uri:
 description: |-
 Common S3 URI for all data capture tiers. Each tier will write to a specific prefix within this bucket.
 Must use s3:// protocol (required by ALB access logs).
 If not provided, the TLS certificate bucket will be used for data capture storage.
 maxLength: 512
 pattern: ^s3://([^/]+)(/[^,=]*)?$
 type: string
 sagemakerEndpoint:
 description: Configuration for SageMaker Endpoint level data capture
 (Tier 1)
 properties:
 captureContentTypeHeader:
 description: Configuration for how to treat different content
 type headers during capture
 properties:
 csvContentTypes:
 description: |-
 List of content type headers to treat as CSV
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: text/csv, application/csv
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 jsonContentTypes:
 description: |-
 List of content type headers to treat as JSON
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: application/json, application/jsonlines
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 type: object
 captureOptions:
 description: Capture options (Input, Output, or both). Defaults
 to [Input, Output] when enabled.
 items:
 description: CaptureOption defines what data to capture
 (input, output, or both).
 properties:
 captureMode:
 description: 'Capture mode: Input or Output'
 enum:
 - Input
 - Output
 type: string
 required:
 - captureMode
 type: object
 maxItems: 32
 minItems: 1
 type: array
 enabled:
 description: Enable or disable SageMaker endpoint data capture
 type: boolean
 initialSamplingPercentage:
 description: Percentage of requests to capture (0-100). Defaults
 to 100 when enabled.
 format: int32
 maximum: 100
 minimum: 0
 type: integer
 kmsKeyId:
 description: Optional KMS key ID, ARN, alias name, or alias
 ARN for encrypting captured data
 maxLength: 2048
 pattern: ^[a-zA-Z0-9:/_-]*$
 type: string
 required:
 - enabled
 type: object
 type: object
 dnsConfig:
 description: DNS automation configuration for Route53. Requires tlsConfig.customCertificateConfig
 to be set.
 properties:
 hostedZoneId:
 description: Route53 Hosted Zone ID where the DNS record will
 be created.
 pattern: ^Z[A-Z0-9]+$
 type: string
 required:
 - hostedZoneId
 type: object
 endpointName:
 description: |-
 Name used for Sagemaker Endpoint
Expand DownExpand Up@@ -589,7 +794,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -636,7 +841,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -2230,6 +2435,14 @@ spec:
 maxLength: 253
 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$
 type: string
 serviceAccountName:
 description: |-
 Name of the Kubernetes ServiceAccount to use for the inference pod.
 If not specified, the namespace's default service account will be used.
 This is useful for providing AWS credentials via IRSA to init containers or the worker.
 maxLength: 253
 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$
 type: string
 volumes:
 description: |-
 Additional volumes to add to the pod spec.
Expand DownExpand Up@@ -4249,13 +4462,59 @@ spec:
 required:
 - fileSystemId
 type: object
 huggingFaceModel:
 description: HuggingFace model configuration. Required when modelSourceType
 is "huggingface".
 properties:
 commitSHA:
 description: |-
 Git commit SHA for the model revision. Must be a full 40-character lowercase hex SHA.
 If not provided, the operator defaults to "main" branch.
 pattern: ^[0-9a-f]{40}$
 type: string
 modelId:
 description: HuggingFace Hub model identifier in org/model
 format (e.g. "meta-llama/Llama-3.1-8B-Instruct").
 pattern: ^[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+$
 type: string
 tokenSecretRef:
 description: |-
 Reference to a Kubernetes Secret containing the HuggingFace API token.
 The token is injected as the HF_TOKEN environment variable into the InitContainer only.
 properties:
 key:
 description: The key of the secret to select from. Must
 be a valid secret key.
 type: string
 name:
 default: ""
 description: |-
 Name of the referent.
 This field is effectively required, but due to backwards compatibility is
 allowed to be empty. Instances of this type with an empty value here are
 almost certainly wrong.
 More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
 type: string
 optional:
 description: Specify whether the Secret or its key must
 be defined
 type: boolean
 required:
 - key
 type: object
 x-kubernetes-map-type: atomic
 required:
 - modelId
 type: object
 modelLocation:
 description: Specific location where the model data exists
 type: string
 modelSourceType:
 enum:
 - fsx
 - s3
 - huggingface
 - kubernetesVolume
 type: string
 prefetchEnabled:
 default: false
Expand DownExpand Up@@ -5492,6 +5751,44 @@ spec:
 - lastUpdated
 - name
 type: object
 dnsStatus:
 description: Status of the operator-managed Route53 DNS record
 properties:
 dnsHealth:
 description: 'DNS resolution status: Active, Pending, or Error.'
 enum:
 - Active
 - Pending
 - Error
 type: string
 hostedZoneId:
 description: Route53 hosted zone ID.
 type: string
 lastTransitionTime:
 description: When the status last transitioned, used for propagation
 timeout.
 format: date-time
 type: string
 managedByOperator:
 description: Whether the operator manages this DNS record.
 type: boolean
 message:
 description: Human-readable status or error message.
 type: string
 previousHostedZoneId:
 description: Previous hosted zone ID, retained during domain/zone
 changes until cleanup completes.
 type: string
 previousRecordName:
 description: Previous record name, retained during domain/zone
 changes until cleanup completes.
 type: string
 recordName:
 description: Route53 record name.
 type: string
 required:
 - managedByOperator
 type: object
 endpoints:
 description: EndpointStatus contains the status of SageMaker endpoints
 properties:
Expand DownExpand Up@@ -5801,7 +6098,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand Down
Loading
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Auto-enable theater mode on YouTube
(function() {
function tryTheater() {
var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]');
if (btn && !btn.classList.contains('activated')) {
btn.click();
}
}
// Try immediately
tryTheater();
// Try after navigation (SPA)
var lastUrl = location.href;
setInterval(function() {
if (location.href !== lastUrl) {
lastUrl = location.href;
setTimeout(tryTheater, 500);
}
}, 1000);
// Also try on player load
var observer = new MutationObserver(tryTheater);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
[Inference Operator] Update CRDs and Helm chart to v3.1#412

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Open

zicanl-amazon
wants to merge
1
commit into

base:main
Choose a base branch

from

 Open


[Inference Operator] Update CRDs and Helm chart to v3.1
#412
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


4 changes: 2 additions & 2 deletions
helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -15,7 +15,7 @@ type: application
# This is the chart version. This version number should be incremented each time you make changes
# to the chart and its templates, including the app version.
# Versions are expected to follow Semantic Versioning (https://semver.org/)
version: 2.1.0
version: 2.2.0

# This is the version number of the application being deployed. Keep this aligned 
# with operator image MAJOR.MINOR version.
Expand DownExpand Up@@ -50,4 +50,4 @@ dependencies:
 alias: keda
 version: 2.17.1
 repository: "https://kedacore.github.io/charts"
 condition: keda.enabled
 condition: keda.enabled

307 changes: 302 additions & 5 deletions
...ence-operator/config/crd/inference.sagemaker.aws.amazon.com_inferenceendpointconfigs.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -270,7 +270,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -315,7 +315,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -343,6 +343,211 @@ spec:
 minimum: 0
 type: integer
 type: object
 dataCapture:
 description: Configuration for data capture across multiple tiers
 (SageMaker, LoadBalancer, Model Pod)
 properties:
 loadBalancer:
 description: Configuration for LoadBalancer level data capture
 (Tier 2)
 properties:
 enabled:
 description: Enable or disable load balancer access logs
 type: boolean
 required:
 - enabled
 type: object
 modelPod:
 description: Configuration for Model Pod level data capture (Tier
 3)
 properties:
 bufferConfig:
 description: Configuration for buffering and flushing captured
 data
 properties:
 batchSize:
 default: 10
 description: Number of records to batch before writing
 to S3
 format: int32
 maximum: 1000
 minimum: 1
 type: integer
 flushIntervalSeconds:
 default: 60
 description: Flush interval in seconds
 format: int32
 maximum: 300
 minimum: 10
 type: integer
 type: object
 captureContentTypeHeader:
 description: Configuration for how to treat different content
 type headers during capture
 properties:
 csvContentTypes:
 description: |-
 List of content type headers to treat as CSV
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: text/csv, application/csv
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 jsonContentTypes:
 description: |-
 List of content type headers to treat as JSON
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: application/json, application/jsonlines
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 type: object
 captureOptions:
 description: Capture options (Input, Output, or both). Defaults
 to [Input, Output] when enabled.
 items:
 description: CaptureOption defines what data to capture
 (input, output, or both).
 properties:
 captureMode:
 description: 'Capture mode: Input or Output'
 enum:
 - Input
 - Output
 type: string
 required:
 - captureMode
 type: object
 maxItems: 32
 minItems: 1
 type: array
 enabled:
 description: Enable or disable model pod data capture
 type: boolean
 initialSamplingPercentage:
 description: Percentage of requests to capture (0-100). Defaults
 to 100 when enabled.
 format: int32
 maximum: 100
 minimum: 0
 type: integer
 kmsKeyId:
 description: Optional KMS key ID, ARN, alias name, or alias
 ARN for encrypting captured data
 maxLength: 2048
 pattern: ^[a-zA-Z0-9:/_-]*$
 type: string
 payloadConfig:
 description: Configuration for payload size limits
 properties:
 maxPayloadSizeKB:
 default: 0
 description: Maximum payload size in KB to capture. 0
 means no limit (capture full payload).
 format: int32
 maximum: 10240
 minimum: 0
 type: integer
 type: object
 required:
 - enabled
 type: object
 s3Uri:
 description: |-
 Common S3 URI for all data capture tiers. Each tier will write to a specific prefix within this bucket.
 Must use s3:// protocol (required by ALB access logs).
 If not provided, the TLS certificate bucket will be used for data capture storage.
 maxLength: 512
 pattern: ^s3://([^/]+)(/[^,=]*)?$
 type: string
 sagemakerEndpoint:
 description: Configuration for SageMaker Endpoint level data capture
 (Tier 1)
 properties:
 captureContentTypeHeader:
 description: Configuration for how to treat different content
 type headers during capture
 properties:
 csvContentTypes:
 description: |-
 List of content type headers to treat as CSV
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: text/csv, application/csv
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 jsonContentTypes:
 description: |-
 List of content type headers to treat as JSON
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: application/json, application/jsonlines
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 type: object
 captureOptions:
 description: Capture options (Input, Output, or both). Defaults
 to [Input, Output] when enabled.
 items:
 description: CaptureOption defines what data to capture
 (input, output, or both).
 properties:
 captureMode:
 description: 'Capture mode: Input or Output'
 enum:
 - Input
 - Output
 type: string
 required:
 - captureMode
 type: object
 maxItems: 32
 minItems: 1
 type: array
 enabled:
 description: Enable or disable SageMaker endpoint data capture
 type: boolean
 initialSamplingPercentage:
 description: Percentage of requests to capture (0-100). Defaults
 to 100 when enabled.
 format: int32
 maximum: 100
 minimum: 0
 type: integer
 kmsKeyId:
 description: Optional KMS key ID, ARN, alias name, or alias
 ARN for encrypting captured data
 maxLength: 2048
 pattern: ^[a-zA-Z0-9:/_-]*$
 type: string
 required:
 - enabled
 type: object
 type: object
 dnsConfig:
 description: DNS automation configuration for Route53. Requires tlsConfig.customCertificateConfig
 to be set.
 properties:
 hostedZoneId:
 description: Route53 Hosted Zone ID where the DNS record will
 be created.
 pattern: ^Z[A-Z0-9]+$
 type: string
 required:
 - hostedZoneId
 type: object
 endpointName:
 description: |-
 Name used for Sagemaker Endpoint
Expand DownExpand Up@@ -589,7 +794,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -636,7 +841,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -2230,6 +2435,14 @@ spec:
 maxLength: 253
 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$
 type: string
 serviceAccountName:
 description: |-
 Name of the Kubernetes ServiceAccount to use for the inference pod.
 If not specified, the namespace's default service account will be used.
 This is useful for providing AWS credentials via IRSA to init containers or the worker.
 maxLength: 253
 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$
 type: string
 volumes:
 description: |-
 Additional volumes to add to the pod spec.
Expand DownExpand Up@@ -4249,13 +4462,59 @@ spec:
 required:
 - fileSystemId
 type: object
 huggingFaceModel:
 description: HuggingFace model configuration. Required when modelSourceType
 is "huggingface".
 properties:
 commitSHA:
 description: |-
 Git commit SHA for the model revision. Must be a full 40-character lowercase hex SHA.
 If not provided, the operator defaults to "main" branch.
 pattern: ^[0-9a-f]{40}$
 type: string
 modelId:
 description: HuggingFace Hub model identifier in org/model
 format (e.g. "meta-llama/Llama-3.1-8B-Instruct").
 pattern: ^[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+$
 type: string
 tokenSecretRef:
 description: |-
 Reference to a Kubernetes Secret containing the HuggingFace API token.
 The token is injected as the HF_TOKEN environment variable into the InitContainer only.
 properties:
 key:
 description: The key of the secret to select from. Must
 be a valid secret key.
 type: string
 name:
 default: ""
 description: |-
 Name of the referent.
 This field is effectively required, but due to backwards compatibility is
 allowed to be empty. Instances of this type with an empty value here are
 almost certainly wrong.
 More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
 type: string
 optional:
 description: Specify whether the Secret or its key must
 be defined
 type: boolean
 required:
 - key
 type: object
 x-kubernetes-map-type: atomic
 required:
 - modelId
 type: object
 modelLocation:
 description: Specific location where the model data exists
 type: string
 modelSourceType:
 enum:
 - fsx
 - s3
 - huggingface
 - kubernetesVolume
 type: string
 prefetchEnabled:
 default: false
Expand DownExpand Up@@ -5492,6 +5751,44 @@ spec:
 - lastUpdated
 - name
 type: object
 dnsStatus:
 description: Status of the operator-managed Route53 DNS record
 properties:
 dnsHealth:
 description: 'DNS resolution status: Active, Pending, or Error.'
 enum:
 - Active
 - Pending
 - Error
 type: string
 hostedZoneId:
 description: Route53 hosted zone ID.
 type: string
 lastTransitionTime:
 description: When the status last transitioned, used for propagation
 timeout.
 format: date-time
 type: string
 managedByOperator:
 description: Whether the operator manages this DNS record.
 type: boolean
 message:
 description: Human-readable status or error message.
 type: string
 previousHostedZoneId:
 description: Previous hosted zone ID, retained during domain/zone
 changes until cleanup completes.
 type: string
 previousRecordName:
 description: Previous record name, retained during domain/zone
 changes until cleanup completes.
 type: string
 recordName:
 description: Route53 record name.
 type: string
 required:
 - managedByOperator
 type: object
 endpoints:
 description: EndpointStatus contains the status of SageMaker endpoints
 properties:
Expand DownExpand Up@@ -5801,7 +6098,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand Down
Loading
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Remove or un-stick sticky/fixed headers that block content
(function() {
function unstick() {
document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) {
if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {
el.style.position = 'static';
el.style.top = 'auto';
el.style.zIndex = 'auto';
}
});
}
unstick();
var observer = new MutationObserver(unstick);
observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });
})();
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
[Inference Operator] Update CRDs and Helm chart to v3.1#412

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Open

zicanl-amazon
wants to merge
1
commit into

base:main
Choose a base branch

from

 Open


[Inference Operator] Update CRDs and Helm chart to v3.1
#412
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


4 changes: 2 additions & 2 deletions
helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -15,7 +15,7 @@ type: application
# This is the chart version. This version number should be incremented each time you make changes
# to the chart and its templates, including the app version.
# Versions are expected to follow Semantic Versioning (https://semver.org/)
version: 2.1.0
version: 2.2.0

# This is the version number of the application being deployed. Keep this aligned 
# with operator image MAJOR.MINOR version.
Expand DownExpand Up@@ -50,4 +50,4 @@ dependencies:
 alias: keda
 version: 2.17.1
 repository: "https://kedacore.github.io/charts"
 condition: keda.enabled
 condition: keda.enabled

307 changes: 302 additions & 5 deletions
...ence-operator/config/crd/inference.sagemaker.aws.amazon.com_inferenceendpointconfigs.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -270,7 +270,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -315,7 +315,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -343,6 +343,211 @@ spec:
 minimum: 0
 type: integer
 type: object
 dataCapture:
 description: Configuration for data capture across multiple tiers
 (SageMaker, LoadBalancer, Model Pod)
 properties:
 loadBalancer:
 description: Configuration for LoadBalancer level data capture
 (Tier 2)
 properties:
 enabled:
 description: Enable or disable load balancer access logs
 type: boolean
 required:
 - enabled
 type: object
 modelPod:
 description: Configuration for Model Pod level data capture (Tier
 3)
 properties:
 bufferConfig:
 description: Configuration for buffering and flushing captured
 data
 properties:
 batchSize:
 default: 10
 description: Number of records to batch before writing
 to S3
 format: int32
 maximum: 1000
 minimum: 1
 type: integer
 flushIntervalSeconds:
 default: 60
 description: Flush interval in seconds
 format: int32
 maximum: 300
 minimum: 10
 type: integer
 type: object
 captureContentTypeHeader:
 description: Configuration for how to treat different content
 type headers during capture
 properties:
 csvContentTypes:
 description: |-
 List of content type headers to treat as CSV
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: text/csv, application/csv
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 jsonContentTypes:
 description: |-
 List of content type headers to treat as JSON
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: application/json, application/jsonlines
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 type: object
 captureOptions:
 description: Capture options (Input, Output, or both). Defaults
 to [Input, Output] when enabled.
 items:
 description: CaptureOption defines what data to capture
 (input, output, or both).
 properties:
 captureMode:
 description: 'Capture mode: Input or Output'
 enum:
 - Input
 - Output
 type: string
 required:
 - captureMode
 type: object
 maxItems: 32
 minItems: 1
 type: array
 enabled:
 description: Enable or disable model pod data capture
 type: boolean
 initialSamplingPercentage:
 description: Percentage of requests to capture (0-100). Defaults
 to 100 when enabled.
 format: int32
 maximum: 100
 minimum: 0
 type: integer
 kmsKeyId:
 description: Optional KMS key ID, ARN, alias name, or alias
 ARN for encrypting captured data
 maxLength: 2048
 pattern: ^[a-zA-Z0-9:/_-]*$
 type: string
 payloadConfig:
 description: Configuration for payload size limits
 properties:
 maxPayloadSizeKB:
 default: 0
 description: Maximum payload size in KB to capture. 0
 means no limit (capture full payload).
 format: int32
 maximum: 10240
 minimum: 0
 type: integer
 type: object
 required:
 - enabled
 type: object
 s3Uri:
 description: |-
 Common S3 URI for all data capture tiers. Each tier will write to a specific prefix within this bucket.
 Must use s3:// protocol (required by ALB access logs).
 If not provided, the TLS certificate bucket will be used for data capture storage.
 maxLength: 512
 pattern: ^s3://([^/]+)(/[^,=]*)?$
 type: string
 sagemakerEndpoint:
 description: Configuration for SageMaker Endpoint level data capture
 (Tier 1)
 properties:
 captureContentTypeHeader:
 description: Configuration for how to treat different content
 type headers during capture
 properties:
 csvContentTypes:
 description: |-
 List of content type headers to treat as CSV
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: text/csv, application/csv
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 jsonContentTypes:
 description: |-
 List of content type headers to treat as JSON
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: application/json, application/jsonlines
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 type: object
 captureOptions:
 description: Capture options (Input, Output, or both). Defaults
 to [Input, Output] when enabled.
 items:
 description: CaptureOption defines what data to capture
 (input, output, or both).
 properties:
 captureMode:
 description: 'Capture mode: Input or Output'
 enum:
 - Input
 - Output
 type: string
 required:
 - captureMode
 type: object
 maxItems: 32
 minItems: 1
 type: array
 enabled:
 description: Enable or disable SageMaker endpoint data capture
 type: boolean
 initialSamplingPercentage:
 description: Percentage of requests to capture (0-100). Defaults
 to 100 when enabled.
 format: int32
 maximum: 100
 minimum: 0
 type: integer
 kmsKeyId:
 description: Optional KMS key ID, ARN, alias name, or alias
 ARN for encrypting captured data
 maxLength: 2048
 pattern: ^[a-zA-Z0-9:/_-]*$
 type: string
 required:
 - enabled
 type: object
 type: object
 dnsConfig:
 description: DNS automation configuration for Route53. Requires tlsConfig.customCertificateConfig
 to be set.
 properties:
 hostedZoneId:
 description: Route53 Hosted Zone ID where the DNS record will
 be created.
 pattern: ^Z[A-Z0-9]+$
 type: string
 required:
 - hostedZoneId
 type: object
 endpointName:
 description: |-
 Name used for Sagemaker Endpoint
Expand DownExpand Up@@ -589,7 +794,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -636,7 +841,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -2230,6 +2435,14 @@ spec:
 maxLength: 253
 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$
 type: string
 serviceAccountName:
 description: |-
 Name of the Kubernetes ServiceAccount to use for the inference pod.
 If not specified, the namespace's default service account will be used.
 This is useful for providing AWS credentials via IRSA to init containers or the worker.
 maxLength: 253
 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$
 type: string
 volumes:
 description: |-
 Additional volumes to add to the pod spec.
Expand DownExpand Up@@ -4249,13 +4462,59 @@ spec:
 required:
 - fileSystemId
 type: object
 huggingFaceModel:
 description: HuggingFace model configuration. Required when modelSourceType
 is "huggingface".
 properties:
 commitSHA:
 description: |-
 Git commit SHA for the model revision. Must be a full 40-character lowercase hex SHA.
 If not provided, the operator defaults to "main" branch.
 pattern: ^[0-9a-f]{40}$
 type: string
 modelId:
 description: HuggingFace Hub model identifier in org/model
 format (e.g. "meta-llama/Llama-3.1-8B-Instruct").
 pattern: ^[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+$
 type: string
 tokenSecretRef:
 description: |-
 Reference to a Kubernetes Secret containing the HuggingFace API token.
 The token is injected as the HF_TOKEN environment variable into the InitContainer only.
 properties:
 key:
 description: The key of the secret to select from. Must
 be a valid secret key.
 type: string
 name:
 default: ""
 description: |-
 Name of the referent.
 This field is effectively required, but due to backwards compatibility is
 allowed to be empty. Instances of this type with an empty value here are
 almost certainly wrong.
 More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
 type: string
 optional:
 description: Specify whether the Secret or its key must
 be defined
 type: boolean
 required:
 - key
 type: object
 x-kubernetes-map-type: atomic
 required:
 - modelId
 type: object
 modelLocation:
 description: Specific location where the model data exists
 type: string
 modelSourceType:
 enum:
 - fsx
 - s3
 - huggingface
 - kubernetesVolume
 type: string
 prefetchEnabled:
 default: false
Expand DownExpand Up@@ -5492,6 +5751,44 @@ spec:
 - lastUpdated
 - name
 type: object
 dnsStatus:
 description: Status of the operator-managed Route53 DNS record
 properties:
 dnsHealth:
 description: 'DNS resolution status: Active, Pending, or Error.'
 enum:
 - Active
 - Pending
 - Error
 type: string
 hostedZoneId:
 description: Route53 hosted zone ID.
 type: string
 lastTransitionTime:
 description: When the status last transitioned, used for propagation
 timeout.
 format: date-time
 type: string
 managedByOperator:
 description: Whether the operator manages this DNS record.
 type: boolean
 message:
 description: Human-readable status or error message.
 type: string
 previousHostedZoneId:
 description: Previous hosted zone ID, retained during domain/zone
 changes until cleanup completes.
 type: string
 previousRecordName:
 description: Previous record name, retained during domain/zone
 changes until cleanup completes.
 type: string
 recordName:
 description: Route53 record name.
 type: string
 required:
 - managedByOperator
 type: object
 endpoints:
 description: EndpointStatus contains the status of SageMaker endpoints
 properties:
Expand DownExpand Up@@ -5801,7 +6098,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand Down
Loading
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Universal Dark Mode - works on any site
(function() {
var enabled = true;
function applyDarkMode() {
if (!enabled) return;
// Create style element if it doesn't exist
var style = document.getElementById('universal-dark-mode-style');
if (!style) {
style = document.createElement('style');
style.id = 'universal-dark-mode-style';
document.head.appendChild(style);
}
// Dark mode CSS - inverts colors but preserves images/video
style.textContent = '
/* Invert everything except media */
html {
filter: invert(1) hue-rotate(180deg) !important;
background: #1a1a2e !important;
}
/* Restore images, videos, iframes, canvas */
img, video, iframe, canvas, svg, picture, [style*="background-image"] {
filter: invert(1) hue-rotate(180deg) !important;
}
/* Preserve specific elements that should not be inverted */
.no-dark-mode, .no-dark-mode *,
[data-theme="light"], [data-theme="light"],
.ace_editor, .ace_editor *,
.CodeMirror, .CodeMirror *,
.monaco-editor, .monaco-editor *,
.markdown-body pre, .markdown-body pre *,
.highlight, .highlight *,
pre code, pre code * {
filter: none !important;
}
/* Fix common UI elements */
.modal, .popup, .dropdown-menu, .tooltip, .popover {
filter: invert(1) hue-rotate(180deg) !important;
background: #2d2d44 !important;
border-color: #444 !important;
}
/* Scrollbars */
::-webkit-scrollbar { background: #1a1a2e !important; }
::-webkit-scrollbar-thumb { background: #444 !important; }
::-webkit-scrollbar-thumb:hover { background: #555 !important; }
/* Selection */
::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
';
}
function removeDarkMode() {
var style = document.getElementById('universal-dark-mode-style');
if (style) style.remove();
}
// Toggle with Alt+Shift+D
document.addEventListener('keydown', function(e) {
if (e.altKey && e.shiftKey && e.key === 'D') {
e.preventDefault();
enabled = !enabled;
if (enabled) {
applyDarkMode();
console.log('[Universal Dark Mode] Enabled');
} else {
removeDarkMode();
console.log('[Universal Dark Mode] Disabled');
}
}
});
// Apply on load
applyDarkMode();
// Re-apply on dynamic content
var observer = new MutationObserver(function(mutations) {
if (enabled && !document.getElementById('universal-dark-mode-style')) {
applyDarkMode();
}
});
observer.observe(document.head, { childList: true });
console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');
})();
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
[Inference Operator] Update CRDs and Helm chart to v3.1#412

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Open

zicanl-amazon
wants to merge
1
commit into

base:main
Choose a base branch

from

 Open


[Inference Operator] Update CRDs and Helm chart to v3.1
#412
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


4 changes: 2 additions & 2 deletions
helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -15,7 +15,7 @@ type: application
# This is the chart version. This version number should be incremented each time you make changes
# to the chart and its templates, including the app version.
# Versions are expected to follow Semantic Versioning (https://semver.org/)
version: 2.1.0
version: 2.2.0

# This is the version number of the application being deployed. Keep this aligned 
# with operator image MAJOR.MINOR version.
Expand DownExpand Up@@ -50,4 +50,4 @@ dependencies:
 alias: keda
 version: 2.17.1
 repository: "https://kedacore.github.io/charts"
 condition: keda.enabled
 condition: keda.enabled

307 changes: 302 additions & 5 deletions
...ence-operator/config/crd/inference.sagemaker.aws.amazon.com_inferenceendpointconfigs.yaml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -270,7 +270,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -315,7 +315,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -343,6 +343,211 @@ spec:
 minimum: 0
 type: integer
 type: object
 dataCapture:
 description: Configuration for data capture across multiple tiers
 (SageMaker, LoadBalancer, Model Pod)
 properties:
 loadBalancer:
 description: Configuration for LoadBalancer level data capture
 (Tier 2)
 properties:
 enabled:
 description: Enable or disable load balancer access logs
 type: boolean
 required:
 - enabled
 type: object
 modelPod:
 description: Configuration for Model Pod level data capture (Tier
 3)
 properties:
 bufferConfig:
 description: Configuration for buffering and flushing captured
 data
 properties:
 batchSize:
 default: 10
 description: Number of records to batch before writing
 to S3
 format: int32
 maximum: 1000
 minimum: 1
 type: integer
 flushIntervalSeconds:
 default: 60
 description: Flush interval in seconds
 format: int32
 maximum: 300
 minimum: 10
 type: integer
 type: object
 captureContentTypeHeader:
 description: Configuration for how to treat different content
 type headers during capture
 properties:
 csvContentTypes:
 description: |-
 List of content type headers to treat as CSV
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: text/csv, application/csv
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 jsonContentTypes:
 description: |-
 List of content type headers to treat as JSON
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: application/json, application/jsonlines
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 type: object
 captureOptions:
 description: Capture options (Input, Output, or both). Defaults
 to [Input, Output] when enabled.
 items:
 description: CaptureOption defines what data to capture
 (input, output, or both).
 properties:
 captureMode:
 description: 'Capture mode: Input or Output'
 enum:
 - Input
 - Output
 type: string
 required:
 - captureMode
 type: object
 maxItems: 32
 minItems: 1
 type: array
 enabled:
 description: Enable or disable model pod data capture
 type: boolean
 initialSamplingPercentage:
 description: Percentage of requests to capture (0-100). Defaults
 to 100 when enabled.
 format: int32
 maximum: 100
 minimum: 0
 type: integer
 kmsKeyId:
 description: Optional KMS key ID, ARN, alias name, or alias
 ARN for encrypting captured data
 maxLength: 2048
 pattern: ^[a-zA-Z0-9:/_-]*$
 type: string
 payloadConfig:
 description: Configuration for payload size limits
 properties:
 maxPayloadSizeKB:
 default: 0
 description: Maximum payload size in KB to capture. 0
 means no limit (capture full payload).
 format: int32
 maximum: 10240
 minimum: 0
 type: integer
 type: object
 required:
 - enabled
 type: object
 s3Uri:
 description: |-
 Common S3 URI for all data capture tiers. Each tier will write to a specific prefix within this bucket.
 Must use s3:// protocol (required by ALB access logs).
 If not provided, the TLS certificate bucket will be used for data capture storage.
 maxLength: 512
 pattern: ^s3://([^/]+)(/[^,=]*)?$
 type: string
 sagemakerEndpoint:
 description: Configuration for SageMaker Endpoint level data capture
 (Tier 1)
 properties:
 captureContentTypeHeader:
 description: Configuration for how to treat different content
 type headers during capture
 properties:
 csvContentTypes:
 description: |-
 List of content type headers to treat as CSV
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: text/csv, application/csv
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 jsonContentTypes:
 description: |-
 List of content type headers to treat as JSON
 Each item must be 1-256 characters and match pattern: [a-zA-Z0-9](-*[a-zA-Z0-9])*/[a-zA-Z0-9](-*[a-zA-Z0-9.])*
 Example: application/json, application/jsonlines
 items:
 type: string
 maxItems: 10
 minItems: 1
 type: array
 x-kubernetes-list-type: set
 type: object
 captureOptions:
 description: Capture options (Input, Output, or both). Defaults
 to [Input, Output] when enabled.
 items:
 description: CaptureOption defines what data to capture
 (input, output, or both).
 properties:
 captureMode:
 description: 'Capture mode: Input or Output'
 enum:
 - Input
 - Output
 type: string
 required:
 - captureMode
 type: object
 maxItems: 32
 minItems: 1
 type: array
 enabled:
 description: Enable or disable SageMaker endpoint data capture
 type: boolean
 initialSamplingPercentage:
 description: Percentage of requests to capture (0-100). Defaults
 to 100 when enabled.
 format: int32
 maximum: 100
 minimum: 0
 type: integer
 kmsKeyId:
 description: Optional KMS key ID, ARN, alias name, or alias
 ARN for encrypting captured data
 maxLength: 2048
 pattern: ^[a-zA-Z0-9:/_-]*$
 type: string
 required:
 - enabled
 type: object
 type: object
 dnsConfig:
 description: DNS automation configuration for Route53. Requires tlsConfig.customCertificateConfig
 to be set.
 properties:
 hostedZoneId:
 description: Route53 Hosted Zone ID where the DNS record will
 be created.
 pattern: ^Z[A-Z0-9]+$
 type: string
 required:
 - hostedZoneId
 type: object
 endpointName:
 description: |-
 Name used for Sagemaker Endpoint
Expand DownExpand Up@@ -589,7 +794,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -636,7 +841,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand DownExpand Up@@ -2230,6 +2435,14 @@ spec:
 maxLength: 253
 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$
 type: string
 serviceAccountName:
 description: |-
 Name of the Kubernetes ServiceAccount to use for the inference pod.
 If not specified, the namespace's default service account will be used.
 This is useful for providing AWS credentials via IRSA to init containers or the worker.
 maxLength: 253
 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$
 type: string
 volumes:
 description: |-
 Additional volumes to add to the pod spec.
Expand DownExpand Up@@ -4249,13 +4462,59 @@ spec:
 required:
 - fileSystemId
 type: object
 huggingFaceModel:
 description: HuggingFace model configuration. Required when modelSourceType
 is "huggingface".
 properties:
 commitSHA:
 description: |-
 Git commit SHA for the model revision. Must be a full 40-character lowercase hex SHA.
 If not provided, the operator defaults to "main" branch.
 pattern: ^[0-9a-f]{40}$
 type: string
 modelId:
 description: HuggingFace Hub model identifier in org/model
 format (e.g. "meta-llama/Llama-3.1-8B-Instruct").
 pattern: ^[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+$
 type: string
 tokenSecretRef:
 description: |-
 Reference to a Kubernetes Secret containing the HuggingFace API token.
 The token is injected as the HF_TOKEN environment variable into the InitContainer only.
 properties:
 key:
 description: The key of the secret to select from. Must
 be a valid secret key.
 type: string
 name:
 default: ""
 description: |-
 Name of the referent.
 This field is effectively required, but due to backwards compatibility is
 allowed to be empty. Instances of this type with an empty value here are
 almost certainly wrong.
 More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
 type: string
 optional:
 description: Specify whether the Secret or its key must
 be defined
 type: boolean
 required:
 - key
 type: object
 x-kubernetes-map-type: atomic
 required:
 - modelId
 type: object
 modelLocation:
 description: Specific location where the model data exists
 type: string
 modelSourceType:
 enum:
 - fsx
 - s3
 - huggingface
 - kubernetesVolume
 type: string
 prefetchEnabled:
 default: false
Expand DownExpand Up@@ -5492,6 +5751,44 @@ spec:
 - lastUpdated
 - name
 type: object
 dnsStatus:
 description: Status of the operator-managed Route53 DNS record
 properties:
 dnsHealth:
 description: 'DNS resolution status: Active, Pending, or Error.'
 enum:
 - Active
 - Pending
 - Error
 type: string
 hostedZoneId:
 description: Route53 hosted zone ID.
 type: string
 lastTransitionTime:
 description: When the status last transitioned, used for propagation
 timeout.
 format: date-time
 type: string
 managedByOperator:
 description: Whether the operator manages this DNS record.
 type: boolean
 message:
 description: Human-readable status or error message.
 type: string
 previousHostedZoneId:
 description: Previous hosted zone ID, retained during domain/zone
 changes until cleanup completes.
 type: string
 previousRecordName:
 description: Previous record name, retained during domain/zone
 changes until cleanup completes.
 type: string
 recordName:
 description: Route53 record name.
 type: string
 required:
 - managedByOperator
 type: object
 endpoints:
 description: EndpointStatus contains the status of SageMaker endpoints
 properties:
Expand DownExpand Up@@ -5801,7 +6098,7 @@ spec:
 type: string
 serverAddress:
 description: Server address for AMP workspace
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+\/[a-zA-Z0-9-]+$|^$
 pattern: ^https:\/\/aps-workspaces\.[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*\.amazonaws\.com\/workspaces\/ws-[a-zA-Z0-9-]+$|^$
 type: string
 targetValue:
 description: Target metric value for scaling
Expand Down
Loading
Loading