1개 답변
- 최신
- 최다 투표
- 가장 많은 댓글
1
Hi there - thanks for opening this thread. Multi-model endpoints are not supported on GPU instance types, see here: https://docs.aws.amazon.com/sagemaker/latest/dg/multi-model-endpoints.html#multi-model-endpoint-instance
In order to host a multi-model endpoint, choose a CPU instance type instead. The ECR image for CPUs will contain the required com.amazonaws.sagemaker.capabilities.multi-models=true
label, see here: https://github.com/aws/deep-learning-containers/blob/master/pytorch/inference/docker/1.8/py3/Dockerfile.cpu
답변함 2년 전
관련 콘텐츠
- AWS 공식업데이트됨 8달 전
Thanks for your help. I struggle with this problem FOR A MONTH. X) My Best Person at this month is you!