dmlc/dgl

Serving DGL models in production

Ouverte

#4 442 ouverte le 21 août 2022

 (1 commentaire) (0 réaction) (0 personne assignée)Python (2 928 forks)batch import
feature requesthelp wanted

Métriques du dépôt

Stars
 (12 665 étoiles)
Métriques de merge PR
 (Métriques PR en attente)

Description

Can you share the best practices for serving DGL models in production? (which of the frameworks is preferred/fully supported - torch serve , TensorFlow serving , Kserve or anything kubeflow based , Nvidia Triton .) There are very few resources on the same.

Guide contributeur