Issue when sending parallel requests

[lschaupp]

Hello,

I am getting the following error when I send multiple requests in parallel to the inference endpoint:

ERROR: 503
{
"code": 503,
"type": "ServiceUnavailableException",
"message": "Model "restorer" has no worker to serve inference request. Please use scale workers API to add workers. If this is a sequence inference, please check if it is closed, or expired; or exceeds maxSequenceJobQueueSize"
}

I have two separate processes that can access the inference API.
Any ideas?

[yurkoff-mv]

Hello!
Please increase job_queue_size in config.properties or in command line.