11## Check Quota Availability Before Deployment
22
3- Before deploying the accelerator, ** ensure sufficient quota availability** for the required model.
3+ Before deploying the accelerator, ** ensure sufficient quota availability** for the required model.
4+ > ** For Global Standard | GPT-4o - the capacity to at least 150k tokens post-deployment for optimal performance.**
5+
6+ > ** For Standard | GPT-4 - ensure a minimum of 30k–40k tokens for best results.**
47
58### Login if you have not done so already
69```
710azd auth login
811```
912
13+
1014### 📌 Default Models & Capacities:
1115```
1216gpt-4o:30
@@ -20,33 +24,40 @@ eastus, uksouth, eastus2, northcentralus, swedencentral, westus, westus2, southc
2024- Only model(s) provided → The script will check for those models in the default regions.
2125- Only region(s) provided → The script will check default models in the specified regions.
2226- Both models and regions provided → The script will check those models in the specified regions.
27+ - ` --verbose ` passed → Enables detailed logging output for debugging and traceability.
2328
2429### ** Input Formats**
25- ✔️ Run without parameters to check default models & regions:
30+ > Use the --models, --regions, and --verbose options for parameter handling:
31+
32+ ✔️ Run without parameters to check default models & regions without verbose logging:
2633 ```
2734 ./quota_check_params.sh
2835 ```
29- ✔️ Model name and required capacity in the format:
36+ ✔️ Enable verbose logging:
37+ ```
38+ ./quota_check_params.sh --verbose
39+ ```
40+ ✔️ Check specific model(s) in default regions:
3041 ```
31- ./quota_check_params.sh gpt-4o:30
42+ ./quota_check_params.sh --models gpt-4o:30
3243 ```
33- ✔️ Multiple models can be passed, separated by commas :
44+ ✔️ Check default models in specific region(s) :
3445 ```
35- ./quota_check_params.sh gpt-4o:30,text-embedding-ada-002:80
46+ ./quota_check_params.sh --regions eastus,westus
3647 ```
3748✔️ Passing Both models and regions:
3849 ```
39- ./quota_check_params.sh gpt-4o:30 eastus,westus2
50+ ./quota_check_params.sh --models gpt-4o:30 --regions eastus,westus2
4051 ```
41- ✔️ Check default models in specific regions :
52+ ✔️ All parameters combined :
4253 ```
43- ./quota_check_params.sh "" eastus,westus2
54+ ./quota_check_params.sh --models gpt-4:30 --regions eastus,westus --verbose
4455 ```
4556
4657### ** Sample Output**
4758The final table lists regions with available quota. You can select any of these regions for deployment.
4859
49- ![ quota-check-ouput] ( Images /quota-check-output.png)
60+ ![ quota-check-ouput] ( images /quota-check-output.png)
5061
5162---
5263### ** If using Azure Portal and Cloud Shell**
@@ -67,7 +78,7 @@ The final table lists regions with available quota. You can select any of these
6778# ## **If using VS Code or Codespaces**
68791. Open the terminal in VS Code or Codespaces.
69802. If you' re using VS Code, click the dropdown on the right side of the terminal window, and select `Git Bash`.
70- 
81+ 
71823. Navigate to the `scripts` folder where the script files are located and make the script as executable:
7283 ```sh
7384 cd infra/scripts
0 commit comments