Skip to content

Commit 0e1fe39

Browse files
author
awstools
committed
feat(client-sagemaker): This release introduces compute quota for GPU, Trainium accelerators, vCPU, and vCPU memory utilization across teams in HyperPod clusters
1 parent 74fe668 commit 0e1fe39

File tree

7 files changed

+139
-7
lines changed

7 files changed

+139
-7
lines changed

‎clients/client-sagemaker/src/commands/CreateComputeQuotaCommand.ts

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -44,6 +44,9 @@ export interface CreateComputeQuotaCommandOutput extends CreateComputeQuotaRespo
4444
* { // ComputeQuotaResourceConfig
4545
* InstanceType: "ml.p4d.24xlarge" || "ml.p4de.24xlarge" || "ml.p5.48xlarge" || "ml.trn1.32xlarge" || "ml.trn1n.32xlarge" || "ml.g5.xlarge" || "ml.g5.2xlarge" || "ml.g5.4xlarge" || "ml.g5.8xlarge" || "ml.g5.12xlarge" || "ml.g5.16xlarge" || "ml.g5.24xlarge" || "ml.g5.48xlarge" || "ml.c5.large" || "ml.c5.xlarge" || "ml.c5.2xlarge" || "ml.c5.4xlarge" || "ml.c5.9xlarge" || "ml.c5.12xlarge" || "ml.c5.18xlarge" || "ml.c5.24xlarge" || "ml.c5n.large" || "ml.c5n.2xlarge" || "ml.c5n.4xlarge" || "ml.c5n.9xlarge" || "ml.c5n.18xlarge" || "ml.m5.large" || "ml.m5.xlarge" || "ml.m5.2xlarge" || "ml.m5.4xlarge" || "ml.m5.8xlarge" || "ml.m5.12xlarge" || "ml.m5.16xlarge" || "ml.m5.24xlarge" || "ml.t3.medium" || "ml.t3.large" || "ml.t3.xlarge" || "ml.t3.2xlarge" || "ml.g6.xlarge" || "ml.g6.2xlarge" || "ml.g6.4xlarge" || "ml.g6.8xlarge" || "ml.g6.16xlarge" || "ml.g6.12xlarge" || "ml.g6.24xlarge" || "ml.g6.48xlarge" || "ml.gr6.4xlarge" || "ml.gr6.8xlarge" || "ml.g6e.xlarge" || "ml.g6e.2xlarge" || "ml.g6e.4xlarge" || "ml.g6e.8xlarge" || "ml.g6e.16xlarge" || "ml.g6e.12xlarge" || "ml.g6e.24xlarge" || "ml.g6e.48xlarge" || "ml.p5e.48xlarge" || "ml.p5en.48xlarge" || "ml.p6-b200.48xlarge" || "ml.trn2.48xlarge" || "ml.c6i.large" || "ml.c6i.xlarge" || "ml.c6i.2xlarge" || "ml.c6i.4xlarge" || "ml.c6i.8xlarge" || "ml.c6i.12xlarge" || "ml.c6i.16xlarge" || "ml.c6i.24xlarge" || "ml.c6i.32xlarge" || "ml.m6i.large" || "ml.m6i.xlarge" || "ml.m6i.2xlarge" || "ml.m6i.4xlarge" || "ml.m6i.8xlarge" || "ml.m6i.12xlarge" || "ml.m6i.16xlarge" || "ml.m6i.24xlarge" || "ml.m6i.32xlarge" || "ml.r6i.large" || "ml.r6i.xlarge" || "ml.r6i.2xlarge" || "ml.r6i.4xlarge" || "ml.r6i.8xlarge" || "ml.r6i.12xlarge" || "ml.r6i.16xlarge" || "ml.r6i.24xlarge" || "ml.r6i.32xlarge" || "ml.i3en.large" || "ml.i3en.xlarge" || "ml.i3en.2xlarge" || "ml.i3en.3xlarge" || "ml.i3en.6xlarge" || "ml.i3en.12xlarge" || "ml.i3en.24xlarge" || "ml.m7i.large" || "ml.m7i.xlarge" || "ml.m7i.2xlarge" || "ml.m7i.4xlarge" || "ml.m7i.8xlarge" || "ml.m7i.12xlarge" || "ml.m7i.16xlarge" || "ml.m7i.24xlarge" || "ml.m7i.48xlarge" || "ml.r7i.large" || "ml.r7i.xlarge" || "ml.r7i.2xlarge" || "ml.r7i.4xlarge" || "ml.r7i.8xlarge" || "ml.r7i.12xlarge" || "ml.r7i.16xlarge" || "ml.r7i.24xlarge" || "ml.r7i.48xlarge", // required
4646
* Count: Number("int"),
47+
* Accelerators: Number("int"),
48+
* VCpu: Number("float"),
49+
* MemoryInGiB: Number("float"),
4750
* },
4851
* ],
4952
* ResourceSharingConfig: { // ResourceSharingConfig

‎clients/client-sagemaker/src/commands/DescribeComputeQuotaCommand.ts

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -55,6 +55,9 @@ export interface DescribeComputeQuotaCommandOutput extends DescribeComputeQuotaR
5555
* // { // ComputeQuotaResourceConfig
5656
* // InstanceType: "ml.p4d.24xlarge" || "ml.p4de.24xlarge" || "ml.p5.48xlarge" || "ml.trn1.32xlarge" || "ml.trn1n.32xlarge" || "ml.g5.xlarge" || "ml.g5.2xlarge" || "ml.g5.4xlarge" || "ml.g5.8xlarge" || "ml.g5.12xlarge" || "ml.g5.16xlarge" || "ml.g5.24xlarge" || "ml.g5.48xlarge" || "ml.c5.large" || "ml.c5.xlarge" || "ml.c5.2xlarge" || "ml.c5.4xlarge" || "ml.c5.9xlarge" || "ml.c5.12xlarge" || "ml.c5.18xlarge" || "ml.c5.24xlarge" || "ml.c5n.large" || "ml.c5n.2xlarge" || "ml.c5n.4xlarge" || "ml.c5n.9xlarge" || "ml.c5n.18xlarge" || "ml.m5.large" || "ml.m5.xlarge" || "ml.m5.2xlarge" || "ml.m5.4xlarge" || "ml.m5.8xlarge" || "ml.m5.12xlarge" || "ml.m5.16xlarge" || "ml.m5.24xlarge" || "ml.t3.medium" || "ml.t3.large" || "ml.t3.xlarge" || "ml.t3.2xlarge" || "ml.g6.xlarge" || "ml.g6.2xlarge" || "ml.g6.4xlarge" || "ml.g6.8xlarge" || "ml.g6.16xlarge" || "ml.g6.12xlarge" || "ml.g6.24xlarge" || "ml.g6.48xlarge" || "ml.gr6.4xlarge" || "ml.gr6.8xlarge" || "ml.g6e.xlarge" || "ml.g6e.2xlarge" || "ml.g6e.4xlarge" || "ml.g6e.8xlarge" || "ml.g6e.16xlarge" || "ml.g6e.12xlarge" || "ml.g6e.24xlarge" || "ml.g6e.48xlarge" || "ml.p5e.48xlarge" || "ml.p5en.48xlarge" || "ml.p6-b200.48xlarge" || "ml.trn2.48xlarge" || "ml.c6i.large" || "ml.c6i.xlarge" || "ml.c6i.2xlarge" || "ml.c6i.4xlarge" || "ml.c6i.8xlarge" || "ml.c6i.12xlarge" || "ml.c6i.16xlarge" || "ml.c6i.24xlarge" || "ml.c6i.32xlarge" || "ml.m6i.large" || "ml.m6i.xlarge" || "ml.m6i.2xlarge" || "ml.m6i.4xlarge" || "ml.m6i.8xlarge" || "ml.m6i.12xlarge" || "ml.m6i.16xlarge" || "ml.m6i.24xlarge" || "ml.m6i.32xlarge" || "ml.r6i.large" || "ml.r6i.xlarge" || "ml.r6i.2xlarge" || "ml.r6i.4xlarge" || "ml.r6i.8xlarge" || "ml.r6i.12xlarge" || "ml.r6i.16xlarge" || "ml.r6i.24xlarge" || "ml.r6i.32xlarge" || "ml.i3en.large" || "ml.i3en.xlarge" || "ml.i3en.2xlarge" || "ml.i3en.3xlarge" || "ml.i3en.6xlarge" || "ml.i3en.12xlarge" || "ml.i3en.24xlarge" || "ml.m7i.large" || "ml.m7i.xlarge" || "ml.m7i.2xlarge" || "ml.m7i.4xlarge" || "ml.m7i.8xlarge" || "ml.m7i.12xlarge" || "ml.m7i.16xlarge" || "ml.m7i.24xlarge" || "ml.m7i.48xlarge" || "ml.r7i.large" || "ml.r7i.xlarge" || "ml.r7i.2xlarge" || "ml.r7i.4xlarge" || "ml.r7i.8xlarge" || "ml.r7i.12xlarge" || "ml.r7i.16xlarge" || "ml.r7i.24xlarge" || "ml.r7i.48xlarge", // required
5757
* // Count: Number("int"),
58+
* // Accelerators: Number("int"),
59+
* // VCpu: Number("float"),
60+
* // MemoryInGiB: Number("float"),
5861
* // },
5962
* // ],
6063
* // ResourceSharingConfig: { // ResourceSharingConfig

‎clients/client-sagemaker/src/commands/ListComputeQuotasCommand.ts

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -62,6 +62,9 @@ export interface ListComputeQuotasCommandOutput extends ListComputeQuotasRespons
6262
* // { // ComputeQuotaResourceConfig
6363
* // InstanceType: "ml.p4d.24xlarge" || "ml.p4de.24xlarge" || "ml.p5.48xlarge" || "ml.trn1.32xlarge" || "ml.trn1n.32xlarge" || "ml.g5.xlarge" || "ml.g5.2xlarge" || "ml.g5.4xlarge" || "ml.g5.8xlarge" || "ml.g5.12xlarge" || "ml.g5.16xlarge" || "ml.g5.24xlarge" || "ml.g5.48xlarge" || "ml.c5.large" || "ml.c5.xlarge" || "ml.c5.2xlarge" || "ml.c5.4xlarge" || "ml.c5.9xlarge" || "ml.c5.12xlarge" || "ml.c5.18xlarge" || "ml.c5.24xlarge" || "ml.c5n.large" || "ml.c5n.2xlarge" || "ml.c5n.4xlarge" || "ml.c5n.9xlarge" || "ml.c5n.18xlarge" || "ml.m5.large" || "ml.m5.xlarge" || "ml.m5.2xlarge" || "ml.m5.4xlarge" || "ml.m5.8xlarge" || "ml.m5.12xlarge" || "ml.m5.16xlarge" || "ml.m5.24xlarge" || "ml.t3.medium" || "ml.t3.large" || "ml.t3.xlarge" || "ml.t3.2xlarge" || "ml.g6.xlarge" || "ml.g6.2xlarge" || "ml.g6.4xlarge" || "ml.g6.8xlarge" || "ml.g6.16xlarge" || "ml.g6.12xlarge" || "ml.g6.24xlarge" || "ml.g6.48xlarge" || "ml.gr6.4xlarge" || "ml.gr6.8xlarge" || "ml.g6e.xlarge" || "ml.g6e.2xlarge" || "ml.g6e.4xlarge" || "ml.g6e.8xlarge" || "ml.g6e.16xlarge" || "ml.g6e.12xlarge" || "ml.g6e.24xlarge" || "ml.g6e.48xlarge" || "ml.p5e.48xlarge" || "ml.p5en.48xlarge" || "ml.p6-b200.48xlarge" || "ml.trn2.48xlarge" || "ml.c6i.large" || "ml.c6i.xlarge" || "ml.c6i.2xlarge" || "ml.c6i.4xlarge" || "ml.c6i.8xlarge" || "ml.c6i.12xlarge" || "ml.c6i.16xlarge" || "ml.c6i.24xlarge" || "ml.c6i.32xlarge" || "ml.m6i.large" || "ml.m6i.xlarge" || "ml.m6i.2xlarge" || "ml.m6i.4xlarge" || "ml.m6i.8xlarge" || "ml.m6i.12xlarge" || "ml.m6i.16xlarge" || "ml.m6i.24xlarge" || "ml.m6i.32xlarge" || "ml.r6i.large" || "ml.r6i.xlarge" || "ml.r6i.2xlarge" || "ml.r6i.4xlarge" || "ml.r6i.8xlarge" || "ml.r6i.12xlarge" || "ml.r6i.16xlarge" || "ml.r6i.24xlarge" || "ml.r6i.32xlarge" || "ml.i3en.large" || "ml.i3en.xlarge" || "ml.i3en.2xlarge" || "ml.i3en.3xlarge" || "ml.i3en.6xlarge" || "ml.i3en.12xlarge" || "ml.i3en.24xlarge" || "ml.m7i.large" || "ml.m7i.xlarge" || "ml.m7i.2xlarge" || "ml.m7i.4xlarge" || "ml.m7i.8xlarge" || "ml.m7i.12xlarge" || "ml.m7i.16xlarge" || "ml.m7i.24xlarge" || "ml.m7i.48xlarge" || "ml.r7i.large" || "ml.r7i.xlarge" || "ml.r7i.2xlarge" || "ml.r7i.4xlarge" || "ml.r7i.8xlarge" || "ml.r7i.12xlarge" || "ml.r7i.16xlarge" || "ml.r7i.24xlarge" || "ml.r7i.48xlarge", // required
6464
* // Count: Number("int"),
65+
* // Accelerators: Number("int"),
66+
* // VCpu: Number("float"),
67+
* // MemoryInGiB: Number("float"),
6568
* // },
6669
* // ],
6770
* // ResourceSharingConfig: { // ResourceSharingConfig

‎clients/client-sagemaker/src/commands/UpdateComputeQuotaCommand.ts

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -43,6 +43,9 @@ export interface UpdateComputeQuotaCommandOutput extends UpdateComputeQuotaRespo
4343
* { // ComputeQuotaResourceConfig
4444
* InstanceType: "ml.p4d.24xlarge" || "ml.p4de.24xlarge" || "ml.p5.48xlarge" || "ml.trn1.32xlarge" || "ml.trn1n.32xlarge" || "ml.g5.xlarge" || "ml.g5.2xlarge" || "ml.g5.4xlarge" || "ml.g5.8xlarge" || "ml.g5.12xlarge" || "ml.g5.16xlarge" || "ml.g5.24xlarge" || "ml.g5.48xlarge" || "ml.c5.large" || "ml.c5.xlarge" || "ml.c5.2xlarge" || "ml.c5.4xlarge" || "ml.c5.9xlarge" || "ml.c5.12xlarge" || "ml.c5.18xlarge" || "ml.c5.24xlarge" || "ml.c5n.large" || "ml.c5n.2xlarge" || "ml.c5n.4xlarge" || "ml.c5n.9xlarge" || "ml.c5n.18xlarge" || "ml.m5.large" || "ml.m5.xlarge" || "ml.m5.2xlarge" || "ml.m5.4xlarge" || "ml.m5.8xlarge" || "ml.m5.12xlarge" || "ml.m5.16xlarge" || "ml.m5.24xlarge" || "ml.t3.medium" || "ml.t3.large" || "ml.t3.xlarge" || "ml.t3.2xlarge" || "ml.g6.xlarge" || "ml.g6.2xlarge" || "ml.g6.4xlarge" || "ml.g6.8xlarge" || "ml.g6.16xlarge" || "ml.g6.12xlarge" || "ml.g6.24xlarge" || "ml.g6.48xlarge" || "ml.gr6.4xlarge" || "ml.gr6.8xlarge" || "ml.g6e.xlarge" || "ml.g6e.2xlarge" || "ml.g6e.4xlarge" || "ml.g6e.8xlarge" || "ml.g6e.16xlarge" || "ml.g6e.12xlarge" || "ml.g6e.24xlarge" || "ml.g6e.48xlarge" || "ml.p5e.48xlarge" || "ml.p5en.48xlarge" || "ml.p6-b200.48xlarge" || "ml.trn2.48xlarge" || "ml.c6i.large" || "ml.c6i.xlarge" || "ml.c6i.2xlarge" || "ml.c6i.4xlarge" || "ml.c6i.8xlarge" || "ml.c6i.12xlarge" || "ml.c6i.16xlarge" || "ml.c6i.24xlarge" || "ml.c6i.32xlarge" || "ml.m6i.large" || "ml.m6i.xlarge" || "ml.m6i.2xlarge" || "ml.m6i.4xlarge" || "ml.m6i.8xlarge" || "ml.m6i.12xlarge" || "ml.m6i.16xlarge" || "ml.m6i.24xlarge" || "ml.m6i.32xlarge" || "ml.r6i.large" || "ml.r6i.xlarge" || "ml.r6i.2xlarge" || "ml.r6i.4xlarge" || "ml.r6i.8xlarge" || "ml.r6i.12xlarge" || "ml.r6i.16xlarge" || "ml.r6i.24xlarge" || "ml.r6i.32xlarge" || "ml.i3en.large" || "ml.i3en.xlarge" || "ml.i3en.2xlarge" || "ml.i3en.3xlarge" || "ml.i3en.6xlarge" || "ml.i3en.12xlarge" || "ml.i3en.24xlarge" || "ml.m7i.large" || "ml.m7i.xlarge" || "ml.m7i.2xlarge" || "ml.m7i.4xlarge" || "ml.m7i.8xlarge" || "ml.m7i.12xlarge" || "ml.m7i.16xlarge" || "ml.m7i.24xlarge" || "ml.m7i.48xlarge" || "ml.r7i.large" || "ml.r7i.xlarge" || "ml.r7i.2xlarge" || "ml.r7i.4xlarge" || "ml.r7i.8xlarge" || "ml.r7i.12xlarge" || "ml.r7i.16xlarge" || "ml.r7i.24xlarge" || "ml.r7i.48xlarge", // required
4545
* Count: Number("int"),
46+
* Accelerators: Number("int"),
47+
* VCpu: Number("float"),
48+
* MemoryInGiB: Number("float"),
4649
* },
4750
* ],
4851
* ResourceSharingConfig: { // ResourceSharingConfig

‎clients/client-sagemaker/src/models/models_1.ts

Lines changed: 18 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -706,6 +706,24 @@ export interface ComputeQuotaResourceConfig {
706706
* @public
707707
*/
708708
Count?: number | undefined;
709+
710+
/**
711+
* <p>The number of accelerators to allocate. If you don't specify a value for vCPU and MemoryInGiB, SageMaker AI automatically allocates ratio-based values for those parameters based on the number of accelerators you provide. For example, if you allocate 16 out of 32 total accelerators, SageMaker AI uses the ratio of 0.5 and allocates values to vCPU and MemoryInGiB.</p>
712+
* @public
713+
*/
714+
Accelerators?: number | undefined;
715+
716+
/**
717+
* <p>The number of vCPU to allocate. If you specify a value only for vCPU, SageMaker AI automatically allocates ratio-based values for MemoryInGiB based on this vCPU parameter. For example, if you allocate 20 out of 40 total vCPU, SageMaker AI uses the ratio of 0.5 and allocates values to MemoryInGiB. Accelerators are set to 0.</p>
718+
* @public
719+
*/
720+
VCpu?: number | undefined;
721+
722+
/**
723+
* <p>The amount of memory in GiB to allocate. If you specify a value only for this parameter, SageMaker AI automatically allocates a ratio-based value for vCPU based on this memory that you provide. For example, if you allocate 200 out of 400 total memory in GiB, SageMaker AI uses the ratio of 0.5 and allocates values to vCPU. Accelerators are set to 0.</p>
724+
* @public
725+
*/
726+
MemoryInGiB?: number | undefined;
709727
}
710728

711729
/**

‎clients/client-sagemaker/src/protocols/Aws_json1_1.ts

Lines changed: 64 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -2642,7 +2642,7 @@ export const se_CreateComputeQuotaCommand = async (
26422642
): Promise<__HttpRequest> => {
26432643
const headers: __HeaderBag = sharedHeaders("CreateComputeQuota");
26442644
let body: any;
2645-
body = JSON.stringify(_json(input));
2645+
body = JSON.stringify(se_CreateComputeQuotaRequest(input, context));
26462646
return buildHttpRpcRequest(context, headers, "/", undefined, body);
26472647
};
26482648

@@ -6721,7 +6721,7 @@ export const se_UpdateComputeQuotaCommand = async (
67216721
): Promise<__HttpRequest> => {
67226722
const headers: __HeaderBag = sharedHeaders("UpdateComputeQuota");
67236723
let body: any;
6724-
body = JSON.stringify(_json(input));
6724+
body = JSON.stringify(se_UpdateComputeQuotaRequest(input, context));
67256725
return buildHttpRpcRequest(context, headers, "/", undefined, body);
67266726
};
67276727

@@ -14775,11 +14775,40 @@ const se_BatchTransformInput = (input: BatchTransformInput, context: __SerdeCont
1477514775

1477614776
// se_CompressionTypes omitted.
1477714777

14778-
// se_ComputeQuotaConfig omitted.
14778+
/**
14779+
* serializeAws_json1_1ComputeQuotaConfig
14780+
*/
14781+
const se_ComputeQuotaConfig = (input: ComputeQuotaConfig, context: __SerdeContext): any => {
14782+
return take(input, {
14783+
ComputeQuotaResources: (_) => se_ComputeQuotaResourceConfigList(_, context),
14784+
PreemptTeamTasks: [],
14785+
ResourceSharingConfig: _json,
14786+
});
14787+
};
1477914788

14780-
// se_ComputeQuotaResourceConfig omitted.
14789+
/**
14790+
* serializeAws_json1_1ComputeQuotaResourceConfig
14791+
*/
14792+
const se_ComputeQuotaResourceConfig = (input: ComputeQuotaResourceConfig, context: __SerdeContext): any => {
14793+
return take(input, {
14794+
Accelerators: [],
14795+
Count: [],
14796+
InstanceType: [],
14797+
MemoryInGiB: __serializeFloat,
14798+
VCpu: __serializeFloat,
14799+
});
14800+
};
1478114801

14782-
// se_ComputeQuotaResourceConfigList omitted.
14802+
/**
14803+
* serializeAws_json1_1ComputeQuotaResourceConfigList
14804+
*/
14805+
const se_ComputeQuotaResourceConfigList = (input: ComputeQuotaResourceConfig[], context: __SerdeContext): any => {
14806+
return input
14807+
.filter((e: any) => e != null)
14808+
.map((entry) => {
14809+
return se_ComputeQuotaResourceConfig(entry, context);
14810+
});
14811+
};
1478314812

1478414813
// se_ComputeQuotaTarget omitted.
1478514814

@@ -14862,7 +14891,20 @@ const se_CreateAutoMLJobV2Request = (input: CreateAutoMLJobV2Request, context: _
1486214891

1486314892
// se_CreateCompilationJobRequest omitted.
1486414893

14865-
// se_CreateComputeQuotaRequest omitted.
14894+
/**
14895+
* serializeAws_json1_1CreateComputeQuotaRequest
14896+
*/
14897+
const se_CreateComputeQuotaRequest = (input: CreateComputeQuotaRequest, context: __SerdeContext): any => {
14898+
return take(input, {
14899+
ActivationState: [],
14900+
ClusterArn: [],
14901+
ComputeQuotaConfig: (_) => se_ComputeQuotaConfig(_, context),
14902+
ComputeQuotaTarget: _json,
14903+
Description: [],
14904+
Name: [],
14905+
Tags: _json,
14906+
});
14907+
};
1486614908

1486714909
// se_CreateContextRequest omitted.
1486814910

@@ -18064,7 +18106,19 @@ const se_TuningJobCompletionCriteria = (input: TuningJobCompletionCriteria, cont
1806418106

1806518107
// se_UpdateCodeRepositoryInput omitted.
1806618108

18067-
// se_UpdateComputeQuotaRequest omitted.
18109+
/**
18110+
* serializeAws_json1_1UpdateComputeQuotaRequest
18111+
*/
18112+
const se_UpdateComputeQuotaRequest = (input: UpdateComputeQuotaRequest, context: __SerdeContext): any => {
18113+
return take(input, {
18114+
ActivationState: [],
18115+
ComputeQuotaConfig: (_) => se_ComputeQuotaConfig(_, context),
18116+
ComputeQuotaId: [],
18117+
ComputeQuotaTarget: _json,
18118+
Description: [],
18119+
TargetVersion: [],
18120+
});
18121+
};
1806818122

1806918123
// se_UpdateContextRequest omitted.
1807018124

@@ -20557,8 +20611,11 @@ const de_ComputeQuotaConfig = (output: any, context: __SerdeContext): ComputeQuo
2055720611
*/
2055820612
const de_ComputeQuotaResourceConfig = (output: any, context: __SerdeContext): ComputeQuotaResourceConfig => {
2055920613
return take(output, {
20614+
Accelerators: __expectInt32,
2056020615
Count: __expectInt32,
2056120616
InstanceType: __expectString,
20617+
MemoryInGiB: __limitedParseFloat32,
20618+
VCpu: __limitedParseFloat32,
2056220619
}) as any;
2056320620
};
2056420621

‎codegen/sdk-codegen/aws-models/sagemaker.json

Lines changed: 45 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,15 @@
11
{
22
"smithy": "2.0",
33
"shapes": {
4+
"com.amazonaws.sagemaker#AcceleratorsAmount": {
5+
"type": "integer",
6+
"traits": {
7+
"smithy.api#range": {
8+
"min": 0,
9+
"max": 10000000
10+
}
11+
}
12+
},
413
"com.amazonaws.sagemaker#Accept": {
514
"type": "string",
615
"traits": {
@@ -10317,6 +10326,24 @@
1031710326
"traits": {
1031810327
"smithy.api#documentation": "<p>The number of instances to add to the instance group of a SageMaker HyperPod cluster.</p>"
1031910328
}
10329+
},
10330+
"Accelerators": {
10331+
"target": "com.amazonaws.sagemaker#AcceleratorsAmount",
10332+
"traits": {
10333+
"smithy.api#documentation": "<p>The number of accelerators to allocate. If you don't specify a value for vCPU and MemoryInGiB, SageMaker AI automatically allocates ratio-based values for those parameters based on the number of accelerators you provide. For example, if you allocate 16 out of 32 total accelerators, SageMaker AI uses the ratio of 0.5 and allocates values to vCPU and MemoryInGiB.</p>"
10334+
}
10335+
},
10336+
"VCpu": {
10337+
"target": "com.amazonaws.sagemaker#VCpuAmount",
10338+
"traits": {
10339+
"smithy.api#documentation": "<p>The number of vCPU to allocate. If you specify a value only for vCPU, SageMaker AI automatically allocates ratio-based values for MemoryInGiB based on this vCPU parameter. For example, if you allocate 20 out of 40 total vCPU, SageMaker AI uses the ratio of 0.5 and allocates values to MemoryInGiB. Accelerators are set to 0.</p>"
10340+
}
10341+
},
10342+
"MemoryInGiB": {
10343+
"target": "com.amazonaws.sagemaker#MemoryInGiBAmount",
10344+
"traits": {
10345+
"smithy.api#documentation": "<p>The amount of memory in GiB to allocate. If you specify a value only for this parameter, SageMaker AI automatically allocates a ratio-based value for vCPU based on this memory that you provide. For example, if you allocate 200 out of 400 total memory in GiB, SageMaker AI uses the ratio of 0.5 and allocates values to vCPU. Accelerators are set to 0.</p>"
10346+
}
1032010347
}
1032110348
},
1032210349
"traits": {
@@ -49831,6 +49858,15 @@
4983149858
}
4983249859
}
4983349860
},
49861+
"com.amazonaws.sagemaker#MemoryInGiBAmount": {
49862+
"type": "float",
49863+
"traits": {
49864+
"smithy.api#range": {
49865+
"min": 0,
49866+
"max": 10000000
49867+
}
49868+
}
49869+
},
4983449870
"com.amazonaws.sagemaker#MemoryInMb": {
4983549871
"type": "integer",
4983649872
"traits": {
@@ -80502,6 +80538,15 @@
8050280538
}
8050380539
}
8050480540
},
80541+
"com.amazonaws.sagemaker#VCpuAmount": {
80542+
"type": "float",
80543+
"traits": {
80544+
"smithy.api#range": {
80545+
"min": 0,
80546+
"max": 10000000
80547+
}
80548+
}
80549+
},
8050580550
"com.amazonaws.sagemaker#ValidationFraction": {
8050680551
"type": "float",
8050780552
"traits": {

0 commit comments

Comments
 (0)