Skip to content
By using AWS re:Post, you agree to the AWS re:Post Terms of Use
AWS re:Postre:Post
About re:Post

Cannot Launch EC2 p3.8xlarge instance on Oregon us-west-2

0

Hello, I cannot launch on demand p3.8xlarge instance on Oregon us-west-2. I have a 32 vCPU limit so it should work but get the error "The requested configuration is currently not supported. Please check the documentation for supported configurations" when trying to launch it. I also tested p3.2xlarge and it also does not work.

I tried different AMI combinations and nothing seems to work. I cannot figure out what the problem is. The settings are all on default, and a key pair is selected.

I did the exact same steps and was able to launch a 8vCPU like g6e.xlarge and 2x 4vCPU G instances but P could not get to run.

Any idea what the problem is?

Topics
ComputeGenerative AI on AWS
Tags
Amazon EC2ComputeGenerative AI on AWS
Language
English
asked 10 months ago234 views
2 Answers
3
Accepted Answer

P3 instances are being retired, and new customers are unable to run P3 instances. You can raise a support request to get confirmation from support team.

P4 and higher instances are also available. You can try the just announced p5.4xlarge

p series

You can also try using G instance. Below screenshot show possible options for up to 32 vCPUs

GPU instance

Do note that this is a separate Running On-Demand G and VT instances quota value.

AWS
EXPERT
answered 10 months ago
0

The error message "The requested configuration is currently not supported" when trying to launch p3.2xlarge or p3.8xlarge instances in the US West (Oregon) region could be due to several factors:

  1. Availability Zone limitations: P3 instances may not be available in all Availability Zones within the US West (Oregon) region. Try launching the instance in different Availability Zones within the region.

  2. AMI compatibility: The AMI you're using might not be compatible with P3 instances. P3 instances are GPU-optimized and may require specific AMIs that support GPU acceleration. Try using an AMI specifically designed for GPU workloads, such as AWS Deep Learning AMIs.

  3. Instance configuration: There might be specific configuration requirements for P3 instances that aren't being met in your launch request. Double-check that you're using a supported configuration.

  4. Regional availability: While P3 instances are documented to be available in US West (Oregon), there could be temporary capacity constraints or other regional limitations affecting availability.

Since you were able to successfully launch other GPU instances like g6e.xlarge, your account permissions and vCPU limits are likely not the issue. The problem appears to be specific to the P3 instance family in your chosen configuration.

To resolve this issue, you could try:

answered 10 months ago

You are not logged in. Log in to post an answer.

A good answer clearly answers the question and provides constructive feedback and encourages professional growth in the question asker.

Relevant content