-
Trying to run sample on two devices (Pixel 8 Android 15 with "Enable on-device GenAI Features" enabled, Pixel 9 Pro w/ GrapheneOS w/play services & AICore installed), and I get the following error:
…
-
### Description of the bug:
I'm trying to convert a MobileNetV4 pytorch model to tflite. I get an error regarding the torch_xla library.
### Actual vs expected behavior:
What I get is:
…
-
### Description of the bug:
Hi @pkgoogle ,
i used example c++ code to inference model i transfer, it can show some error.
- my command
```
bazel run -c opt //ai_edge_torch/generative/example…
-
### Description of the bug:
We are using the ai_edge_torch library to convert the Qwen2-0.5 model into TFLite format. We have made the necessary modifications in our own fork, available (https://…
-
### Description of the bug:
When I use `torch.sum()` without specifying a dimension, the model does not get exported properly.
It gets exported correctly if I do specify the dimension
### Actual …
-
### Description of the bug:
I am using Google Colab Pro+ (with High RAM) to convert Llama 3.2 1B Instruct model to Tflite format (for later use in mediapipe android app). For that
1. I downloaded …
-
This tracks related backlogs and epics.
- [ ] A. pub/sub stream support / maintainer: @jaeyun-jung
- [x] A-1. zeromq src(sub) & sink(pub) with ANY: avaiable in opensource (gst-zmq) #3077
…
-
### Description of the bug:
When I convert a pytorch model containing a MaxPool2D module, `ai_edge_torch.convert` crashes. This can be reproduced on my setup using the following minimal repro:
``…
-
See: https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/
-
### Description of the bug:
hi @pkgoogle ,
i try to use convert_gemm2_to_tflite.py to treansfer model. i can see 2 error when i transfer.
- this one i can change loader.py to solve it.
```
…