Sign inJoin
2
3 Comments

Deploying machine learning models

by Ilyas Malgazhdarov

Hi, what is your preferred way of deploying your ML models in production?

Ilyas Malgazhdarov's avatarIlyas Malgazhdarov
on October 20, 2020
Say something nice to ilyaskz7…
Post Comment
  1. 2

    I really like https://developer.nvidia.com/nvidia-triton-inference-server. What is yours?

    angelob's avatar angelob
    ·
    6 years ago
    ·
    Reply
    1. 1

      I shall try it, didn’t deploy anything yet, just looking into possible options.

      Ilyas Malgazhdarov's avatar Ilyas Malgazhdarov
      ·
      6 years ago
      ·
      Reply
      1. 1

        Cool, let me know if you need any help. Here is something I wrote about this topic: https://anbasile.github.io/posts/serving-nlp-models/

        angelob's avatar angelob
        ·
        6 years ago
        ·
        Reply