microsoft / microsoft/onnxruntime

[Feature Request]

Open
#20,010 5 comments 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

Hi, onnx and onnxruntime are great. I have built a tool named [onnxslim](https://github.com/tsingmicro-toolchain/OnnxSlim), which can help optimize onnx model especially large language model, is there any chance that this tool can be used in onnxruntime repo. Thanks.

### Describe scenario use case

```
pip install onnxslim
onnxslim raw.onnx slim.onnx
```
[example ](https://github.com/tsingmicro-toolchain/OnnxSlim/actions/runs/8362295155/job/22892533411#step:4:91)show how onnxslim can slim qwen-1.8b from alibaba

![image](https://github.com/microsoft/onnxruntime/assets/46103969/ccb935cc-4e2a-4f39-a278-fd56da4557d9)

Contributor guide

Open the contributing guide

Research direction

Start with the linked OnnxSlim project and its pip invocation, then review the supplied Qwen slimming example as context. Determine the intended integration scope with ONNX Runtime; done cannot be defined yet because the request names no ONNX Runtime entry point, file, test, or acceptance criteria.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.