# \#sdk

**URL:** https://community.memryx.com/tag/sdk/1.md

[Latest](https://community.memryx.com/latest.md) · [Categories](https://community.memryx.com/categories.md) · [Tags](https://community.memryx.com/tags.md)

---

## [MX3 wedges under concurrent streaming with some DFPs — reproducer, workarounds, and a way to recover without rebooting](https://community.memryx.com/t/mx3-wedges-under-concurrent-streaming-with-some-dfps-reproducer-workarounds-and-a-way-to-recover-without-rebooting/232)

<div class="topic-metadata">

**Author:** [@JESUSROYETH](https://community.memryx.com/u/JESUSROYETH)\
**Replies:** 2\
**Last updated:** [August 17, 2026, 1:19pm UTC](https://community.memryx.com/t/mx3-wedges-under-concurrent-streaming-with-some-dfps-reproducer-workarounds-and-a-way-to-recover-without-rebooting/232 "2026-08-17T13:19:52Z")

</div>

Hi @lindsay.morel and team: Update, same day: I kept measuring and the cause is not what this post says. These DFPs are not broken — they run 3000 frames straight with one inference in flight. The failure needs concurre…

---

## [Model failed ONNX checker validation](https://community.memryx.com/t/model-failed-onnx-checker-validation/221)

<div class="topic-metadata">

**Author:** [@yan12125](https://community.memryx.com/u/yan12125)\
**Replies:** 2\
**Last updated:** [June 16, 2026, 2:52am UTC](https://community.memryx.com/t/model-failed-onnx-checker-validation/221 "2026-06-16T02:52:33Z")

</div>

I’m trying a Transformers model (Tacoin/openpi-pi0.5-libero-onnx at main). mx\_nc reports Model failed ONNX checker validation, while onnx.checker.check\_model('/path/to/model.onnx') does not result in an error. How to fix…

---

## [SDK 2.1 question: placement signals for multi-device / multi-DFP setups](https://community.memryx.com/t/sdk-2-1-question-placement-signals-for-multi-device-multi-dfp-setups/186)

<div class="topic-metadata">

**Author:** [@Jerem6](https://community.memryx.com/u/Jerem6)\
**Replies:** 3\
**Last updated:** [April 1, 2026, 9:32pm UTC](https://community.memryx.com/t/sdk-2-1-question-placement-signals-for-multi-device-multi-dfp-setups/186 "2026-04-01T21:32:09Z")

</div>

Hello all, I’ve been reading through the SDK 2.1 docs and a few related threads, and I had a question about placement in multi-device or multi-DFP setups. When compile-time capabilities and runtime deployment constrain…

---

## [Unable to compile a model](https://community.memryx.com/t/unable-to-compile-a-model/174)

<div class="topic-metadata">

**Author:** [@yan12125](https://community.memryx.com/u/yan12125)\
**Replies:** 6\
**Last updated:** [March 13, 2026, 6:26am UTC](https://community.memryx.com/t/unable-to-compile-a-model/174 "2026-03-13T06:26:25Z")

</div>

I have an ONNX model that causes mx\_nc to report “the model must have a uniform batch dimension throughout the entire model” error. However, the model already have batch size=1 for all layers. How to fix that? The model…

---

## [SDK 2.1 Update now available](https://community.memryx.com/t/sdk-2-1-update-now-available/133)

<div class="topic-metadata">

**Author:** [@sam.fuller](https://community.memryx.com/u/sam.fuller)\
**Replies:** 0\
**Last updated:** [November 4, 2025, 11:55pm UTC](https://community.memryx.com/t/sdk-2-1-update-now-available/133 "2025-11-04T23:55:38Z")

</div>

Adding support for Debian 13 among other updates. More details can be found here: Release Notes — MemryX Developer Hub