Skip to content
By using AWS re:Post, you agree to the AWS re:Post Terms of Use
AWS re:Postre:Post
About re:Post

Questions tagged with ML Ops with Amazon SageMaker and Kubernetes

Kubernetes is an open source system used to automate the deployment, scaling, and management of containerized applications. Kubeflow Pipelines is a workflow manager that offers an interface to manage and schedule machine learning (ML) workflows on a Kubernetes cluster. Using open source tools offers flexibility and standardization, but requires time and effort to set up infrastructure, provision notebook environments for data scientists, and stay up-to-date with the latest deep learning framework versions.

Content language: English

Filter questions
Select tags to filter
Sort by
Sort by most recent
Filter Questions by:

Browse through the questions and answers listed below or filter and sort to narrow down your results.

14 results

Is GPU Serverless inferencing for custom LLM models?

Wanted to check if AWS supports GPU inferencing via serverless compute (dynamic loading), since I don't want to spend $1,5/h for EC2 instance, which my client will use not more than 5 minutes per mont...
Amazon SageMakerServerlessML Ops with Amazon SageMaker and Kubernetes
3
answers
0
votes
1.7K
views

asked 2 years ago

How to use gRPC in Triton Inference Server using SageMaker E...

Hello, I am trying to serve a model using SageMaker Endpoint. I am using Triton Inference Server as a framework, I know that I can enable Triton's gRPC protocol communication by setting the `SAGEMA...
Accepted AnswerAmazon SageMakerAmazon SageMaker DeploymentML Ops with Amazon SageMaker and Kubernetes
1
answers
0
votes
749
views

asked 2 years ago

I can't create a sagemaker project

I was trying to create a sagemaker project using the template "MLOps template for model building, training, and deployment with third-party Git repositories using Jenkins". But I kept getting the err...
AWS CloudFormationAWS CodePipelineML Ops with Amazon SageMaker and KubernetesAWS CodeBuildAmazon SageMaker
2
answers
0
votes
145
views

asked 2 years ago

Inference Recommendation fails due to image size error

Hello AWS team! I am trying to run a suite of inference recommendation jobs leveraging NVIDIA Triton Inference Server on a set of GPU instances (ml.g5.12xlarge, ml.g5.8xlarge, ml.g5.16xlarge) as well...
ServerlessML Ops with Amazon SageMaker and KubernetesAmazon SageMakerAWS LambdaAWS Inferentia
1
answers
0
votes
968
views

asked 2 years ago

SageMaker Inference Recommender: Image size is greater than ...

Hello, I am trying to run a suite of inference recommendation jobs on a set of GPU instances (ml.g5.12xlarge, ml.g5.8xlarge, ml.g5.16xlarge) as well as AWS Inferentia machines (ml.inf2.2xlarge, ml.in...
Amazon SageMaker ExperimentsAWS LambdaMachine Learning & AIML Ops with Amazon SageMaker and KubernetesAmazon SageMaker
1
answers
0
votes
765
views

asked 2 years ago

Best design choice for a custom serverless ML application

Hi, How would one go about designing a serverless ML application in AWS? Currently, our project is using the [serverless framework](https://www.serverless.com/) and lambda functions to accomplish thi...
Accepted AnswerAmazon SageMakerAWS FargateAWS LambdaML Ops with Amazon SageMaker and KubernetesServerless
1
answers
0
votes
627
views

asked 3 years ago

Can I use Sagemaker ScriptProcessor to process a java code, ...

I want to create a training step in sagemaker pipeline, and use custom processor like below. But instead of python code I want to use java code in the place of [code = 'src/processing.py' ]. Is it po...
Accepted AnswerAmazon SageMaker PipelinesJava DevelopmentAmazon SageMakerML Ops with Amazon SageMaker and Kubernetes
1
answers
0
votes
630
views

asked 3 years ago

Architecture review for Custom Anomaly AI

I am trying to build a architecture for custom anomaly ai on AWS for my startup. Please let me know if my way of thinking is correct or not 1. Data Ingestion: Ingesting the data into AWS S3 in JSON fo...
Amazon Quick SightAWS GlueAmazon Simple Storage ServiceML Ops with Amazon SageMaker and KubernetesBuild & Train ML Models
1
answers
0
votes
501
views

asked 3 years ago

Sagemaker Model Monitor - endPointInput:contentType is of ty...

Calling the sagemaker model endpoint with contentType `application/octet-stream` which is also being captured in Data Capture Logs. What would be the ideal way to transform the data such that model mo...
Monitoring & LoggingAmazon SageMakerML Ops with Amazon SageMaker and KubernetesAmazon SageMaker Clarify
1
answers
0
votes
795
views

asked 4 years ago

how to access/set up a model registry ?

based on aws docs/examples (https://docs.aws.amazon.com/sagemaker/latest/dg/model-registry-version.html), one can create/register model that is generated by your training pipeline. first we need to cr...
Machine Learning & AIAmazon SageMakerML Ops with Amazon SageMaker and KubernetesBuild & Train ML Models
1
answers
0
votes
579
views

asked 4 years ago

Tips for managing several ML project with similar framework

Hi, I'm working on an end-to-end ml project which, for the moment, goes from training (it takes already processed train/val/test data from an S3 bucket) to deploy, passing through hyperparameter tun...
Amazon SageMakerDevOpsMachine Learning & AIML Ops with Amazon SageMaker and Kubernetes
1
answers
0
votes
543
views

asked 4 years ago

I cant save neuron model after compile the model into an AWS...

I cant save neuron model after compile the model into an AWS Neuron optimized TorchScript. My code: ``` import tensorflow # to workaround a protobuf version conflict issue import torch import torch....
AWS NeuronML Ops with Amazon SageMaker and KubernetesCompute
1
answers
0
votes
646
views

asked 4 years ago

  • 1
  • 2
  • Page size
    12 / page