Serving DGL models in production
Open
feature request
help wanted
- Dominant language
- Python
- Stars
- 14.3k
- Forks
- 3.1k
- PR merge metrics
- No merged PRs in 30d
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.
Contributor guide
No contributing guide indexed for this repository
Research direction
Start with the issue’s question and compare the serving frameworks it names: TorchServe, TensorFlow Serving, KServe/Kubeflow, and NVIDIA Triton. No files or tests are identified; done would mean providing actionable DGL production-serving guidance and clarifying which options are supported.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- kubernetes, python, pytorch, tensorflow
- Domain
- documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100