All Content tagged with Amazon SageMaker Deployment

Amazon SageMaker provides a broad selection of machine learning (ML) infrastructure and model deployment options to help meet your needs, whether real time or batch. Once you deploy a model, SageMaker creates persistent endpoints to integrate into your applications to make ML predictions (also known as inference). It supports the entire spectrum of inference, from low latency (a few milliseconds) and high throughput (hundreds of thousands of inference requests per second) to long-running inference for use cases such as natural language processing (NLP) and computer vision (CV). Whether you bring your own models and containers or use those provided by AWS, you can implement MLOps best practices using SageMaker to reduce the operational burden of managing ML models at scale.

Content language: English

Select tags to filter
Sort by most recent
88 results
Hi , I have few queries regarding sagemaker. Are there any APIs that will provide- 1. DETAILED info on the running models (instances) deployed on Sagemaker endpoint ? 2. DETAILED info on the list of M...
1
answers
0
votes
42
views
asked 2 months ago
I followed AWS tutorials to deploy a model on Sagemaker, but when the server deployed takes several minutes to process a request, it runs the same processing multiple times for an invocation. I report...
2
answers
0
votes
47
views
asked 2 months ago
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...
1
answers
0
votes
121
views
asked 3 months ago
I am curious about trying canvas, and I was wondering if I can use the models I build in canvas the same way I use the models I have built using automl. Specifically will I be able to use the sagemak...
1
answers
0
votes
105
views
asked 5 months ago
Hi, I created a postgres RDS database which I configured and was able to connect via pgAdmin. However when I try to connect to the db via code, I get timeout error For context my vpc security group r...
2
answers
0
votes
165
views
asked 6 months ago
I am new to AWS and I do not understand a lot things here. I have a trained LSTM model in <model-name>.keras format. I am looking to deploy this model as a batch transformer. I have a custom script t...
1
answers
0
votes
341
views
asked 8 months ago
I am the root user of my aws account ann when I try to create a sagemaker deployment project. I get this error. "You are not authorized to use the Amazon SageMaker project templates. Please contact yo...
1
answers
0
votes
276
views
asked 8 months ago
Hi, I have a docker container containing a custom inference script that keeps failing on endpoint creation with the following error: CannotStartContainerError. Please ensure the model container for v...
1
answers
0
votes
404
views
Hi, I want to deploy a model to sagemaker, however this model takes In different weights depending on some scenarios. Is there any way that I can deploy an endpoint which is able to use different wei...
1
answers
0
votes
307
views
asked 10 months ago
Hi, I've constructed a pipeline using Scikit-Learn on SageMaker, incorporating data transformations and a Random Forest model, then I use the hyperparameter tuner to find the best model. I can unpa...
0
answers
0
votes
127
views
asked 10 months ago
I create a Sagemaker Shadow Test to compare shadow variant with production variant and passed s3 URI to store prediction results of shadow vairant. I have sent more than 100 request to the prod varian...
0
answers
0
votes
72
views
asked a year ago
Hi, Our sagemaker endpoints (async mode) are randomly failing. Here is a snippet of the data-log log stream : ``` 2024-03-05T17:40:10.207-05:00 2024-03-05T22:40:05.261:[sagemaker logs] [e2b81384-05...
0
answers
1
votes
256
views
asked a year ago