JARVIS icon indicating copy to clipboard operation
JARVIS copied to clipboard
verified publisher icon microsoft

Why does it always prompt when starting: "ValueError: The server of local inference endpoints is not running, please start it first. "

Open jiaenqiu opened this issue 2 years ago • 4 comments

image

jiaenqiu avatar Apr 19 '23 06:04 jiaenqiu

I got the exact same issue.... For me, it is caused by the python models_server.py --config configs/config.default.yaml keeping getting killed without any error. Any help will be appreciated.

shuliangmai1 avatar Apr 19 '23 06:04 shuliangmai1

image

Doesn't the startup service execute models_server.py first and then awesome_chat.py?

jiaenqiu avatar Apr 19 '23 07:04 jiaenqiu

I got the exact same issue.... For me, it is caused by the python models_server.py --config configs/config.default.yaml keeping getting killed without any error. Any help will be appreciated.

That happens if you run out of memory. Check your activity monitor.

heathriel avatar Apr 19 '23 17:04 heathriel

That happens if you run out of memory. Check your activity monitor.

Are you sure about this? I get the same error even though I configure for hybrid/minimal as suggested and have 24GB free space. README says it would consume >12GB but, I don't think that it would exceed 24GB, right?

whatactuallyis avatar Jun 18 '23 14:06 whatactuallyis