Skip to content

chore: update model type to global standard #424

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Roopan-Microsoft merged 1 commit into from
Jul 22, 2025
Merged

chore: update model type to global standard #424

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions .github/workflows/CI.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -196,15 +196,15 @@ jobs:
# Increase the TPM for the Azure OpenAI models
echo "Increasing TPM for Azure OpenAI models..."
openai_gpt_deployment_url="/subscriptions/${{ secrets.AZURE_SUBSCRIPTION_ID }}/resourceGroups/${{ env.rg_name }}/providers/Microsoft.CognitiveServices/accounts/$openai_resource_name/deployments/gpt-4o-mini?api-version=2023-05-01"
az rest -m put -u "$openai_gpt_deployment_url" -b "{'sku':{'name':'Standard','capacity':${{ env.GPT_CAPACITY }}},'properties': {'model': {'format': 'OpenAI','name': 'gpt-4o-mini','version': '2024-07-18'}}}"
az rest -m put -u "$openai_gpt_deployment_url" -b "{'sku':{'name':'GlobalStandard','capacity':${{ env.GPT_CAPACITY }}},'properties': {'model': {'format': 'OpenAI','name': 'gpt-4o-mini','version': '2024-07-18'}}}"
if [ $? -ne 0 ]; then
echo "Failed to increase TPM for GPT deployment."
exit 1
else
echo "Successfully increased TPM for GPT deployment."
fi
openai_embedding_deployment_url="/subscriptions/${{ secrets.AZURE_SUBSCRIPTION_ID }}/resourceGroups/${{ env.rg_name }}/providers/Microsoft.CognitiveServices/accounts/$openai_resource_name/deployments/text-embedding-large?api-version=2023-05-01"
az rest -m put -u "$openai_embedding_deployment_url" -b "{'sku':{'name':'Standard','capacity': ${{ env.TEXT_EMBEDDING_CAPACITY }}},'properties': {'model': {'format': 'OpenAI','name': 'text-embedding-3-large','version': '1'}}}"
az rest -m put -u "$openai_embedding_deployment_url" -b "{'sku':{'name':'GlobalStandard','capacity': ${{ env.TEXT_EMBEDDING_CAPACITY }}},'properties': {'model': {'format': 'OpenAI','name': 'text-embedding-3-large','version': '1'}}}"
if [ $? -ne 0 ]; then
echo "Failed to increase TPM for Text Embedding deployment."
exit 1
Expand Down
2 changes: 1 addition & 1 deletion Deployment/bicep/azureopenaiservicemodel.bicep
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ resource gpt4Deployment 'Microsoft.CognitiveServices/accounts/deployments@2023-0
parent: openAIService
name: name
sku: {
name: 'Standard'
name: 'GlobalStandard'
capacity: model.capacity
}
properties: {
Expand Down
4 changes: 2 additions & 2 deletions Deployment/checkquota.ps1
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,8 +45,8 @@ Write-Host "✅ Azure subscription set successfully."

# Define models and their minimum required capacities
$MIN_CAPACITY = @{
"OpenAI.Standard.gpt-4o-mini" = $GPT_MIN_CAPACITY
"OpenAI.Standard.text-embedding-3-large" = $TEXT_EMBEDDING_MIN_CAPACITY
"OpenAI.GlobalStandard.gpt-4o-mini" = $GPT_MIN_CAPACITY
"OpenAI.GlobalStandard.text-embedding-3-large" = $TEXT_EMBEDDING_MIN_CAPACITY
}

$VALID_REGION = ""
Expand Down
4 changes: 2 additions & 2 deletions Deployment/main.bicep
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,7 +119,7 @@ module gs_openaiservicemodels_gpt4o 'bicep/azureopenaiservicemodel.bicep' = {
version: '2024-07-18'
raiPolicyName: ''
capacity: 1
scaleType: 'Standard'
scaleType: 'GlobalStandard'
}

}
Expand All @@ -139,7 +139,7 @@ module gs_openaiservicemodels_text_embedding 'bicep/azureopenaiservicemodel.bice
version: '1'
raiPolicyName: ''
capacity: 1
scaleType: 'Standard'
scaleType: 'GlobalStandard'
}
}
dependsOn: [
Expand Down