OpenNMT Forum

Server, docker and apache2

Hi,

I built a docker image which uses ctranslate2 models in the server. I configured the entrypoint to execute onmt_server. I works perfectly.

The question is, for production purposes, should I configure Apache to serve the onmt_server? I guess I need Apache or similar to run it in production… Should I configure Apache inside the docker?
Thanks

1 Like

I hope this answer (and/or others in the thread) can help:

Kind regards,
Yasmin

1 Like

HI @ymoslem!

Thanks for your answer. However, I do not have any issues when configuring Apache to host the server. My problem is configuring Apache2 inside the docker to host the server.

It seems stuck here when loading with apache2:

[Thu Nov 19 12:02:46.084823 2020] [wsgi:error] [pid 9:tid 140573004527360] Pre-loading model 100
[Thu Nov 19 12:02:46.089834 2020] [wsgi:error] [pid 9:tid 140573004527360] [2020-11-19 12:02:46,089 INFO] Loading tokenizer

nvidia-smi command is not showing anything about the server. It is not loaded

If I run the wsgi script, then it works:

Pre-loading model 100
[2020-11-19 12:05:24,009 INFO] Loading tokenizer
[2020-11-19 12:05:24,074 INFO] Loading model 100
Performed a dummy translation to initialize the model ([[-2.4049062728881836]], [['a']])
Serving on http://0.0.0.0:5000