microsoft / microsoft/onnxruntime
[Feature Request] Simultaneous support for DirectML and TensorRT in NET/nugets
- Dominant language
- C++
- Stars
- 21.9k
- Forks
- 4.2k
- Avg merge
- 4d 11h
- Merged PRs (30d)
- 184
Description
### Describe the feature request
A way to deploy support for both TensorRT EP and DirectML EP at the same time.
Our application is a NET8-based and currently it seems there is no way to get support for both TensorRT and DirectML with the official nugets.
### Describe scenario use case
We want to be able to offert TensorRT EP to our customers, but need DirectML as a fallback (for those customers that do not have NVIDIA GPU).
Contributor guide
Research direction
The issue names no files, tests, or entry points. Start by examining the official .NET 8 NuGet packages and how TensorRT and DirectML execution-provider support is packaged; done means a supported way to deploy both providers with DirectML available as fallback.
Written by the indexing model from the issue text.
Assessment
- Domain
- build-system, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100