Jhen-Jie Hong

Thanks for the PR! It would be helpful if you could provide a valid test file. Also, note that we will replace all native iOS/Android implementations with [RNWhisperJSI](https://github.com/mybigday/whisper.rn/blob/main/cpp/jsi/RNWhisperJSI.cpp) in the...

I can't figure the cause based on the error message. Could you provide more information, like Xcode logs or what models are you using?

I can update llama.cpp tomorrow, but not sure if it will help you. You should be able to get Xcode logs like this: Logs: Load Llama-3.2-1B-Instruct-Q4_K_M.gguf (success) ``` llama_model_loader: loaded...

Can you try [v0.4.8](https://github.com/mybigday/llama.rn/releases/tag/v0.4.8)? > let me share the logs: [...logs] This looks like logs from JS, not Xcode logs.

> lm_ggml_metal_init: error: load pipeline error: Error Domain=AGXMetalA14 Code=3 "Function kernel_add is using language version 3.2 which is incompatible with this OS." UserInfo={NSLocalizedDescription=Function kernel_add is using language version 3.2 which...

> But I set `n_gpu_layers: 0`. Shouldn't that prevent use of metal entirely? Due to llama.cpp changes, the metal kernels still load even set n_gpu_layers: 0, which it used to...

The error of Multiple commands produce usually provide two paths, can you share the another one?

#112 should also solved this issue. Please request to re-open it if the problem still exists in v0.5. Also, this issue may still exists if we choose to build from...

> I am getting this error using 0.5.0: [omitted] It should can be solved by exclude the headers (in cpp/), but I'm not clear how to do in Expo project.

> > > I am getting this error using 0.5.0: [omitted] > > > > > > It should can be solved by exclude the headers (in cpp/), but I'm...