I am trying to create my model endpoint of a fine tuned llama27b on g5.2x or g5.4x but anything apart from g4dn.12xlarge
UnexpectedStatusException: Error hosting endpoint huggingface-pytorch-tgi-inference-2023-xx-xx-xx-xx-xx-xxx: Failed. Reason: The primary container for production variant AllTraffic did not pass the ping health check. Please check CloudWatch logs for this endpoint.
Is this just a vram issue or are there any other problems that need to be addressed as whenever i run the 12x it works fine without any error
I think you need to check CloudWatch to see what really happened.