Jhen-Jie Hong

Use [WASM](https://github.com/ggerganov/whisper.cpp/tree/master/examples/whisper.wasm).

Use onnxruntime packages from fork for test purpose

1

Use @fugood/onnxruntime-react-native for test purpose, which it includes: - Early test for onnxruntime v1.16 (common / react-native only) - Use JSI to do blob exchange instead of base64 (https://github.com/microsoft/onnxruntime/pull/16094) -...

LLaVa support

1

llama.cpp includes LLaVa example (+clip.cpp), we could use it to provide vision support. We may implement it after #30 is done. Also, it will be great if we could make...

llama.cpp now supports parallel decoding in one context so we can support. Breaking change: Deprecate `stopCompletion` method and move to return values of completion.

Context: https://github.com/ggerganov/llama.cpp/discussions/2550 Currently: - only replaced methods related to q2_k / q4_k / q6_k models - not able to get the correct result, need more time to understand Probably won't...

It just like OpenAI text completion playground, start with a text area as prompt. We can also add area for use grammar.

So we can easier to test model params without using debug mode.