Skip to content

dgallitelli/kiro-power-for-sagemaker-ai

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Kiro Power for SageMaker AI

A Kiro Power providing battle-tested guidance for deploying and training ML models on Amazon SageMaker AI. Covers inference endpoints, LLM fine-tuning, HyperPod clusters, Model Monitor, AutoML with AutoGluon, and SageMaker Python SDK v3 patterns — all derived from real deployment experience.

Integrates with the Amazon SageMaker AI MCP Server for HyperPod cluster management.

What's Included

Steering File Topic
model-customization.md Serverless model customization — SFT, DPO, RLVR, RLAIF trainers, reward functions, model evaluation (benchmarks, LLM-as-judge, custom scorers), deployment to SageMaker/Bedrock, supported models list
inference-endpoints.md Real-time endpoint deployment — container selection, DJL LMI/vLLM, DLC env vars, multimodal models
training-jobs.md Fine-tuning with custom scripts — QLoRA/LoRA, GPU vs Trainium, AWS recipes, Training Jobs
hyperpod.md HyperPod cluster setup — EKS orchestration, Training Operator, Task Governance, resiliency
hyperpod-inference.md HyperPod inference — JumpStart, custom models from S3/FSx, CLI/SDK/kubectl, autoscaling, KV caching
model-monitor.md Model monitoring — Data Quality, Model Quality, Bias, Explainability, SDK v3 patterns and known bugs
automl-autogluon.md AutoML — tabular, time series, multimodal, DLC images, SageMaker Pipelines
sdk-v3-reference.md SDK v3 API reference — correct imports, image_uris, deployment patterns, invocation

MCP Tools

Tool Description
manage_hyperpod_stacks Deploy, describe, and delete HyperPod clusters via CloudFormation
manage_hyperpod_cluster_nodes List, describe, update, and delete cluster nodes

Installation

From Local Directory

  1. Clone this repository:

    git clone https://github.com/dgallitelli/kiro-power-for-sagemaker-ai.git
  2. In Kiro, open the Powers panel (sidebar icon or Command Palette -> "Powers")

  3. Click "Add Custom Power" -> "Local Directory"

  4. Paste the absolute path to the cloned repo:

    /path/to/kiro-power-for-sagemaker-ai
    
  5. Click "Add" — the power should appear in your Installed Powers list

From GitHub URL

  1. In Kiro, open the Powers panel

  2. Click "Add Custom Power" -> "Git Repository"

  3. Paste:

    https://github.com/dgallitelli/kiro-power-for-sagemaker-ai
    
  4. Click "Add"

Usage

Once installed, the power activates automatically when you work on SageMaker-related tasks. Kiro loads the relevant steering file based on your query:

  • Ask about serverless model customization, fine-tuning with SFT/DPO/RLVR/RLAIF, or model evaluation -> loads model-customization.md
  • Ask about deploying a model -> loads inference-endpoints.md
  • Ask about custom training scripts or Training Jobs -> loads training-jobs.md
  • Ask about HyperPod -> loads hyperpod.md or hyperpod-inference.md
  • Ask about model monitoring -> loads model-monitor.md
  • Ask about AutoGluon -> loads automl-autogluon.md

You can also explicitly reference steering files in chat using # context.

Requirements

  • Kiro IDE
  • uv (for the SageMaker AI MCP server)
  • AWS CLI configured with credentials

License

Apache-2.0

About

Kiro Power for Amazon SageMaker AI — inference, training, HyperPod, Model Monitor, AutoGluon, SDK v3

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors