I am trying to deploy llama-2 7b model on vertex AI but i am continiously getting Error message: "The following quotas are exceeded: CustomModelServingL4GPUsPerProjectPerRegion" this error
You need to request quota that contains these GPUs
L4 GPUs
Make sure of the Region and that the GPUs for inference not training
@Mustafa_21 But can you tell me how I request quota that contains these GPUs ?
@cloudy_watcher where you able to figure this out? I'm getting the same error.
User | Count |
---|---|
10 | |
2 | |
1 | |
1 | |
1 |