Questions tagged with Amazon Elastic Inference

Lower machine learning inference costs by up to 75%

Content language: English

Select tags to filter
Sort by most recent

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

14 results
Hi , iam trying create a vm using cft which deploys a vm which is getting attached with 2 network interfaces and specified ip address and the issue is while deploying the stacks out of 10 stack creat...
2
answers
0
votes
57
views
asked a month ago
I have an windows EC2 instance in public subnet with a dynamic public IP and a private IP..it has a IIS server running and listening on 0.0.0.0:0 and [::]:0 ..when I try to access the webpage on the d...
4
answers
0
votes
754
views
asked 9 months ago
How is the minimum billing period for a PublicIPv4 calculated? e.g.: 1. If a public IP is auto-allocated (along with ec2 instance) and used for only 10 seconds, is IP billed for the exact 10 seconds o...
1
answers
0
votes
386
views
asked a year ago
Hi Im trying to test a ensemble model created with AWS Sagemaker Autopilot Past a un seen data frame from S3 to AWS Sagemaker Inference Batch Transform Jobsd in .csv format, that weighs 4.4 MB which...
1
answers
0
votes
1K
views
asked a year ago
**Can someone help me load my model to create an endpoint?** Provided explanation of steps followed, error logs and code used to create everything...thank you in advance. I'm trying very hard to in...
2
answers
0
votes
799
views
asked 2 years ago
I am currently using Amazon SageMaker for running my machine learning models, but it is becoming costly. To reduce costs, I am considering two options: AWS Elastic Inference and AWS Inferentia. I not...
2
answers
0
votes
1.5K
views
asked 2 years ago
I'm trying to make a public facing web app that allows for inferencing, with probably ten or so available models to my users. My initial thought was that I would have a front-end basic webpage, that ...
1
answers
0
votes
502
views
asked 2 years ago
We want to proceed with prediction through the Elastic Inference accelerator only when a request comes in to Lambda. If that's the case, will I still be charged when EC2 is up and running? Or are you ...
1
answers
0
votes
534
views
asked 2 years ago
I'm using a standard **AWS EKS** cluster, all cloud based (K8S 1.22) with multiple node groups, one of which uses a Launch Template that defines an Elastic Inference Accelerator attached to the instan...
0
answers
0
votes
300
views
asked 3 years ago
It is mentioned in the AWS EI docs that we can use EI in US EAST, WEST, ASIA PACIFIC, EU. But when i launch an instance in ohio or Seoul, it shows this error > ``` Instance launch failed The Availab...
1
answers
0
votes
849
views
asked 3 years ago
I am using the batch transform function in SageMaker for the inference of my PyTorch model. I am using the same structure as https://github.com/aws/amazon-sagemaker-examples/tree/main/advanced_functio...
0
answers
0
votes
330
views
asked 3 years ago
Hi, After many attempts to use the new create vpc tool that builds the VPC, subnets, gateways, etc. I keep getting to the point where it is allocating IP's and it fails. I have full admin permission...
1
answers
0
votes
543
views
asked 3 years ago
  • 1
  • 2
  • 12 / page