dmlc/dgl

Serving DGL models in production

開放

#4,442 建立於 2022年8月21日

 (1 則留言) (0 個反應) (0 位負責人)Python (2,928 個分叉)batch import
feature requesthelp wanted

倉庫指標

星標
 (12,665 顆星)
PR 合併指標
 (30 天內沒有已合併 PR)

描述

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.

貢獻者指南