[BUG]: Cannot load the backend on MACOS

[AsakusaRinne]

Description

When running examples on my MAC notebook, it got the correct path of the native library but failed to load it.

Here's the output of uname -a of my notebook.

Darwin U-0R7TCJJH-2327.local 22.3.0 Darwin Kernel Version 22.3.0: Mon Jan 30 20:39:46 PST 2023; root:xnu-8792.81.3~2/RELEASE_ARM64_T6020 arm64

Its processor is M2 Pro and system is Ventura 13.2.1.

Here's the full logs.

[llama Debug]: Loading library: 'llama'
[llama Info]: Detected OS Platform: 'OSX'
[llama Debug]: Detected OS string: 'osx-arm64'
[llama Debug]: Detected extension string: '.dylib'
[llama Debug]: Detected prefix string: 'lib'
[llama Info]: NativeLibraryConfig Description:
- LibraryName: LLama
- Path: ''
- PreferCuda: True
- PreferredAvxLevel: NoAVX
- AllowFallback: True
- SkipCheck: False
- SearchDirectories and Priorities: { ./ }
[llama Info]: NativeLibraryConfig Description:
- LibraryName: LLama
- Path: ''
- PreferCuda: True
- PreferredAvxLevel: NoAVX
- AllowFallback: True
- SkipCheck: False
- SearchDirectories and Priorities: { ./ }
[llama Debug]: Got relative library path 'runtimes/osx-arm64/native/libllama.dylib' from local with (NativeLibraryName: LLama, UseCuda: False, AvxLevel: None), trying to load it...
[llama Debug]: Found full path file '/Users/liuyaohui/Downloads/llama_test/bin/Debug/net8.0/runtimes/osx-arm64/native/libllama.dylib' for relative path 'runtimes/osx-arm64/native/libllama.dylib'
[llama Info]: Failed Loading '/Users/liuyaohui/Downloads/llama_test/bin/Debug/net8.0/runtimes/osx-arm64/native/libllama.dylib'
[llama Warning]: No library was loaded before calling native apis. This is not an error under netstandard2.0 but needs attention with net6 or higher.
Unhandled exception. System.TypeInitializationException: The type initializer for 'LLama.Native.NativeApi' threw an exception.

Reproduction Steps

Perhaps only I can reproduce it, just run the examples.

Environment & Configuration

• Operating system: MACOS (Ventura 13.2.1)
• .NET runtime version: .NET 8
• LLamaSharp version: 0.13.0
• CUDA version (if you are using cuda backend): -
• CPU & GPU device: Apple M2 Pro

Known Workarounds

No response

[AsakusaRinne]

@SignalRT I know little about MAC and have no idea about how to move forward to dig it out now. Could you please give me some suggestions?