This message was deleted.
# ask-for-help
s
This message was deleted.
👀 1
🍱 1
a
Can you tell us more about how to reproduce this bug?
did you have another bentoml server running?
y
Initially we didn’t have this issue when running on a centos7 server or mac server etc., but recently we switched to an OCI server and started having this issue. We are also running this within a docker image (ubuntu 18.04), base image is
11.6.0-cudnn8-runtime-ubuntu18.04
b
@Yilun Zhang did you resolve this issue?
y
No not yet
@Bo Further testing and comparison showed it’s only happening with
--production
and it’s working fine without this flag. For a bit more information.
Copy code
# system
Oracle Linux Server release 7.9

# nvidia
NVIDIA-SMI 470.141.03   Driver Version: 470.141.03   CUDA Version: 11.4

# gpus
NVIDIA A100-SXM 40GB

# python
python3.8

# bentoml
1.0.4 (same error after upgrading to 1.0.10)
It might be a bit strict to setup same environment and reproduce the bug. There are very little information about this
circus
error on the web.