However, it's hard to say why it's not found in your container. Are you sure that you use the inference container, not training container, for your endpoint? If you go to the AWS Console > Amazon SageMaker > Models > your model, what ECR image it shows in Container 1 - Image?
It will be useful if you can share the code that you used to setup the SageMaker PyTorch estimator (if any) how you define your PyTorchModel and how you deploy() it.
Should use the Sagemaker image
instead of ec2
SageMaker Multi Model endpoint creation fails while creating for model built on container sagemaker-scikit-learn:0.23-1-cpu-py3asked 6 months ago
Sagemaker Asynchronous Endpoint ConfigurationAccepted Answerasked 6 months ago
How to create a serverless endpoint in sagemaker?asked 9 months ago
Without ECR being enabled in AWS account at Organization Level, what's the impact to SageMaker Studio?Accepted Answerasked 7 months ago
AWS SageMaker - Extending Pre-built Container, Deploy Endpoint Failed. No such file or directory: 'serve'"Accepted Answerasked 2 months ago
How to create (Serverless) SageMaker Endpoint using exiting tensorflow pb (frozen model) file?asked 7 months ago
ECS load container image from sagemaker built-in algorithm docker pathAccepted Answerasked 7 months ago
Extending Docker image for SageMaker Inferenceasked 5 months ago
Sagemaker Async Inference Endpoint: Linking input identifier, container log, output identifier?asked 6 months ago
No such file or directory: '/opt/ml/input/data/test/revenue_train.csv' Sagemaker [SM_CHANNEL_TRAIN]asked 3 months ago