Guy Luz
Guy Luz
The file [coreml_provider_factory.h](https://github.com/microsoft/onnxruntime/blob/main/include/onnxruntime/core/providers/coreml/coreml_provider_factory.h) got updated 2 weeks ago. Ours [coreml_provider_factory.h](https://github.com/gtbluesky/onnxruntime_flutter/blob/main/src/onnxruntime/coreml_provider_factory.h) got updated 2 years ago. I think this affects the performance in my app, as the summary speed is so...
I am trying to summarize a text using the [.onnx file](https://huggingface.co/pszemraj/long-t5-tglobal-base-16384-book-summary/blob/main/model.onnx) from here https://huggingface.co/pszemraj/long-t5-tglobal-base-16384-book-summary. I am getting OrtValue result and I am trying to get the value but the program...
I have used the example project and added [model.onnx](https://huggingface.co/pszemraj/bigbird-pegasus-large-K-booksum/blob/main/onnx/model.onnx) from https://huggingface.co/pszemraj/bigbird-pegasus-large-K-booksum under `assets/models`. Then I have replaced this line ` const assetFileName = 'assets/models/silero_vad.onnx';` with ` const assetFileName = 'assets/models/model.onnx';`...
I would like to run ONNX on my server side that use Dart native. Since we are using ffigen to generate the code, I am wondering how hard it will...
Fix: #271 Updated bertqa example to use: gradle-8.11.1 kotlin 1.9.0 Also cleaned the default pubspec.yaml comments
I would like to run TensorFlow Lite on my server side that use Dart native. Since we are using ffigen to generate the code, I am wondering how hard it...
Currently I am using `Future main() async { Chain.capture(() { myFunction() }; }` and I am not sure where I should add `Chain.terse` if I want to get rid of...
I would like to run Pytourch Lite on my server side that use Dart native. Since we are using pigeon to generate the code, I am wondering how hard it...
I want to use the Qwen3 module on my app. It requires a minimal LLama version `b5401`. Can we update the repo to use a supported version?.