k-dense-ai/edge-embedded-ai-engineer
v1.0.0MIT
Reasons from tensor-arena budgets, full-int8 PTQ with representative calibration, and TFLM/CMSIS-NN or Vela/Ethos-U compile paths through ONNX Runtime QNN HTP and mobile delegates—treating train–serve preprocessing skew, float thresholds on quantized outputs, and NPU operator fallback as first-class failure modes.
| Version | Commit | First seen | Updated |
|---|---|---|---|
| 1.0.0latest | 98c7fae46648 | — |