diff --git a/aml/deployment.yaml b/aml/deployment.yaml index 3b4a9e2e..00a2b15e 100644 --- a/aml/deployment.yaml +++ b/aml/deployment.yaml @@ -1,6 +1,6 @@ $schema: https://azuremlschemas.azureedge.net/latest/managedOnlineDeployment.schema.json name: bloom-deployment -endpoint_name: bloom-inference +endpoint_name: bloom-azure-inference model: azureml:bloom-safetensors:1 model_mount_path: /var/azureml-model environment_variables: @@ -8,7 +8,7 @@ environment_variables: MODEL_ID: bigscience/bloom NUM_SHARD: 8 environment: - image: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference:sha-4e685d9 + image: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference:sha-cd5961b inference_config: liveness_route: port: 80 diff --git a/aml/endpoint.yaml b/aml/endpoint.yaml index f2f01d5e..ed769dcd 100644 --- a/aml/endpoint.yaml +++ b/aml/endpoint.yaml @@ -1,3 +1,3 @@ $schema: https://azuremlsdk2.blob.core.windows.net/latest/managedOnlineEndpoint.schema.json -name: bloom-inference +name: bloom-azure-inference auth_mode: key