text-generation-inference/aml
OlivierDehaene 47ac334a21 0.4.0
2023-03-12 10:06:15 +01:00
..
deployment.yaml 0.4.0 2023-03-12 10:06:15 +01:00
endpoint.yaml increased initial delay 2023-03-07 11:14:31 +01:00
model.yaml feat(ci): push to AML registry (#56) 2023-02-06 14:33:56 +01:00
README.md feat(ci): push to AML registry (#56) 2023-02-06 14:33:56 +01:00

Azure ML endpoint

Create all resources

az ml model create -f model.yaml -g HuggingFace-BLOOM-ModelPage -w HuggingFace
az ml online-endpoint create -f endpoint.yaml -g HuggingFace-BLOOM-ModelPage -w HuggingFace
az ml online-deployment create -f deployment.yaml -g HuggingFace-BLOOM-ModelPage -w HuggingFace

Update deployment

az ml online-deployment update -f deployment.yaml -g HuggingFace-BLOOM-ModelPage -w HuggingFace