Hi, I am trying to use MediaPipe to construct on-device LLM driven agents workflow for academic research. I wonder is it possible to use QNN TFLite Delegate to run LLM like gemma by Java API? Is it possible to delegate a “calculator” node to NPU within a MediaPipe Graph?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| TFLITE to mediapipe | 1 | 124 | June 26, 2024 | |
| Help converting tflite models with mediapipe | 2 | 247 | January 22, 2025 | |
| The Different Between MediaPipe and TFLite | 4 | 1443 | December 27, 2023 | |
| Will the ARM Mali GPU accelerate a Tensor Flow Lite model | 4 | 2038 | June 19, 2023 | |
| AI edge torch api converted Gemma 2b inference via Mediapipe on Android | 0 | 133 | June 26, 2024 |