# References

## Key Features
---

### Real-time Inference
- [AWS Innovate 2021 - Amazon SageMaker 기반 사전 훈련된 딥러닝 모델 손쉽게 배포하기 (김대근 AIML SA)](https://www.youtube.com/watch?v=ZdOcrLKow3I)
- [Developer Guide](https://docs.aws.amazon.com/sagemaker/latest/dg/realtime-endpoints.html)

### Batch Inference
- [AWS AI/ML Blog](https://aws.amazon.com/blogs/machine-learning/performing-batch-inference-with-tensorflow-serving-in-amazon-sagemaker/)
- [Developer Guide](https://docs.aws.amazon.com/sagemaker/latest/dg/batch-transform.html)

### Asynchronous Inference
- [AWS AI/ML Blog](https://aws.amazon.com/ko/blogs/machine-learning/run-computer-vision-inference-on-large-videos-with-amazon-sagemaker-asynchronous-endpoints/)
- [Developer Guide](https://docs.aws.amazon.com/sagemaker/latest/dg/async-inference.html)

### Lambda Serverless Inference
- [AWS AI/ML Blog](https://aws.amazon.com/ko/blogs/korea/new-for-aws-lambda-container-image-support/)
- [SageMaker Python SDK](https://sagemaker.readthedocs.io/en/stable/overview.html?highlight=lambdamodel#serverless-inference)
- [AWS Builders Online - AWS Lambda 컨테이너 이미지 서비스 활용하기 (김태수 SA)](https://www.youtube.com/watch?v=tTg9Lp7Sqok)
  
### SageMaker Serverless Inference
- [AWS AI/ML Blog](https://aws.amazon.com/ko/blogs/machine-learning/deploying-ml-models-using-sagemaker-serverless-inference-preview/)
- [Developer Guide](https://docs.aws.amazon.com/sagemaker/latest/dg/serverless-endpoints.html)

### Multi-container Endpoint
- [AWS AI/ML Blog](https://aws.amazon.com/ko/blogs/machine-learning/deploy-multiple-serving-containers-on-a-single-instance-using-amazon-sagemaker-multi-container-endpoints/)
- [Developer Guide](https://docs.aws.amazon.com/sagemaker/latest/dg/multi-container-endpoints.html)

### Inference Pipeline
- [AWS AI/ML Blog](https://aws.amazon.com/ko/blogs/machine-learning/preprocess-input-data-before-making-predictions-using-amazon-sagemaker-inference-pipelines-and-scikit-learn/)
- [Developer Guide](https://docs.aws.amazon.com/sagemaker/latest/dg/inference-pipelines.html)


<br>
    
## Cost Optimization
---
 
### Model Compilation using SageMaker Neo
- [AWS AI/ML Blog](https://aws.amazon.com/ko/blogs/machine-learning/unlock-performance-gains-with-xgboost-amazon-sagemaker-neo-and-serverless-artillery/)
- [AWS AI/ML Blog - SageMaker Neo](https://aws.amazon.com/ko/blogs/machine-learning/category/artificial-intelligence/amazon-sagemaker-neo/)
- [Developer Guide](https://docs.aws.amazon.com/sagemaker/latest/dg/neo.html)

### Model Compilation for multiple on-devices
- [AWS AI/ML Blog](https://aws.amazon.com/ko/blogs/machine-learning/build-machine-learning-at-the-edge-applications-using-amazon-sagemaker-edge-manager-and-aws-iot-greengrass-v2/)
- [Developer Guide](https://docs.aws.amazon.com/sagemaker/latest/dg/edge.html)

### Elastic Inference
- [AWS AI/ML Blog](https://aws.amazon.com/ko/blogs/machine-learning/reduce-ml-inference-costs-on-amazon-sagemaker-with-hardware-and-software-acceleration/)
- [AWS AI/ML Blog - Elastic Inference](https://aws.amazon.com/ko/blogs/machine-learning/category/artificial-intelligence/amazon-elastic-inference/)
- [Developer Guide](https://docs.aws.amazon.com/elastic-inference/latest/developerguide/basics.html)

<br>

## From PoC to Production
---
 
### A/B Testing
- [AWS AI/ML Blog](https://aws.amazon.com/ko/blogs/machine-learning/a-b-testing-ml-models-in-production-using-amazon-sagemaker/)
- [AWS AI/ML Blog - Advanced](https://aws.amazon.com/ko/blogs/machine-learning/dynamic-a-b-testing-for-machine-learning-models-with-amazon-sagemaker-mlops-projects/)
- [Developer Guide](https://docs.aws.amazon.com/sagemaker/latest/dg/model-ab-testing.html)

### Blue/Green Deployment Guardrail
- [AWS AI/ML Blog](https://aws.amazon.com/ko/blogs/machine-learning/take-advantage-of-advanced-deployment-strategies-using-amazon-sagemaker-deployment-guardrails/)
- [Developer Guide](https://docs.aws.amazon.com/sagemaker/latest/dg/deployment-guardrails.html)

### End-to-end ML pipelines 
- [AWS AI/ML Blog](https://aws.amazon.com/ko/blogs/machine-learning/building-automating-managing-and-scaling-ml-workflows-using-amazon-sagemaker-pipelines/)
- [AWS AI/ML Blog - Advanced](https://aws.amazon.com/ko/blogs/machine-learning/building-a-scalable-machine-learning-pipeline-for-ultra-high-resolution-medical-images-using-amazon-sagemaker/)
- [Developer Guide](https://docs.aws.amazon.com/sagemaker/latest/dg/pipelines.html)

### Korean NLP and Hugging Face
- [KoELECTRA](https://github.com/monologg/KoELECTRA)
- [Naver Sentiment Movie Corpus v1.0](https://github.com/e9t/nsmc)
- [Hugging Face on Amazon SageMaker](https://huggingface.co/docs/sagemaker/main)
- [Hugging Face examples](https://github.com/huggingface/notebooks/tree/master/sagemaker)