# ONNX Runtime Support?

**URL:** <https://discuss.flower.ai/t/onnx-runtime-support/786>\
**Category:** Flower Framework\
**Created:** [March 7, 2025, 3:15pm UTC](https://discuss.flower.ai/t/onnx-runtime-support/786 "2025-03-07T15:15:20Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![williamlm](https://dub1.discourse-cdn.com/flex013/user_avatar/discuss.flower.ai/williamlm/32/162_2.png) [@williamlm](https://discuss.flower.ai/u/williamlm)\
**Post date:** [March 7, 2025, 3:15pm UTC](https://discuss.flower.ai/t/onnx-runtime-support/786/1 "2025-03-07T15:15:20Z")

</div>

# [Discussion Topic] Integrating ONNX Runtime Support into Flower for Enhanced On-Device Training

The ONNX Runtime offers cross-platform capabilities for on-device training across web, mobile, and desktop environments. Integrating ONNX Runtime into Flower could expand its applicability in federated learning scenarios, especially on diverse client devices.

## Discussion Points

**Feasibility and Benefits:**

- What are the potential advantages of supporting ONNX Runtime in Flower?
- How would this integration enhance on-device training capabilities?

**Technical Considerations:**

- What modifications are necessary within Flower to support ONNX Runtime?
- Are there existing challenges or limitations in integrating ONNX models?

**Call to Action:**

We invite Flower community members to share their insights, experiences, and interest regarding the integration of ONNX Runtime into Flower. Feel free to open up a PR if you are interested in supporting this.