microsoft / microsoft/onnxruntime

[Feature Request] Integrate IREE into ort

Open
#20,275 1 comment 0 reactions 0 assignees View on GitHub
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

Open the contributing 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.