Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

increased initial delay

This commit is contained in:
OlivierDehaene 2023-03-07 11:14:31 +01:00
parent 31159266eb
commit f067673a1d
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
aml/deployment.yaml
View File

@ -1,6 +1,6 @@
$schema: https://azuremlschemas.azureedge.net/latest/managedOnlineDeployment.schema.json $schema: https://azuremlschemas.azureedge.net/latest/managedOnlineDeployment.schema.json
name: bloom-deployment name: bloom-deployment
endpoint_name: bloom-azure-inference endpoint_name: bloom-inference
model: azureml:bloom-safetensors:1 model: azureml:bloom-safetensors:1
model_mount_path: /var/azureml-model model_mount_path: /var/azureml-model
environment_variables: environment_variables:
@ -24,13 +24,13 @@ request_settings:
request_timeout_ms: 60000 request_timeout_ms: 60000
max_concurrent_requests_per_instance: 256 max_concurrent_requests_per_instance: 256
liveness_probe: liveness_probe:
initial_delay: 80 initial_delay: 140
timeout: 60 timeout: 60
period: 60 period: 60
success_threshold: 1 success_threshold: 1
failure_threshold: 2 failure_threshold: 2
readiness_probe: readiness_probe:
initial_delay: 80 initial_delay: 140
timeout: 60 timeout: 60
period: 60 period: 60
success_threshold: 1 success_threshold: 1

2
aml/endpoint.yaml
View File

@ -1,3 +1,3 @@
$schema: https://azuremlsdk2.blob.core.windows.net/latest/managedOnlineEndpoint.schema.json $schema: https://azuremlsdk2.blob.core.windows.net/latest/managedOnlineEndpoint.schema.json
name: bloom-azure-inference name: bloom-inference
auth_mode: key auth_mode: key