microsoft / microsoft/onnxruntime
[Feature Request] Integrate IREE into ort
Open
feature request
- Dominant language
- C++
- Stars
- 21.9k
- Forks
- 4.2k
- Avg merge
- 4d 11h
- Merged PRs (30d)
- 184
Description
### Describe the feature request
This request is very similar to the PR #15862 (integrate triton into ort). The only difference are the compilers and the details of metadata. They both use PTX/Cubin to bridge ort and custom kernels.
### Describe scenario use case
Using IREE compiles models and dump the PTX Kernels, integrate those kernels into ORT
Contributor guide
Research direction
Start by reading PR #15862, which describes the similar Triton integration, then compare its compiler and metadata handling with the IREE request. Done means integrating IREE-generated PTX/Cubin kernels into ONNX Runtime for model execution.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, machine-learning
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100