This commit is originally made by lcarrere in https://github.com/SciSharp/LLamaSharp/issues/180 .

I have confirmed this modification is OK in my windows 11 laptop, add make this commit according require of AsakusaRinne.

* Updated binaries to llama.cpp `3ab8b3a92ede46df88bc5a2dfca3777de4a2b2b6` (build run: https://github.com/SciSharp/LLamaSharp/actions/runs/8118890586)

* Added abort callback

* Added properties to get/set thread count on `LLamaContext`

* Fixed LLamaLogLevel numbering

- Re-implmented `Rewind` as an extension method using `Modify` internally
 - Implemented `ShiftLeft`, which shifts everything over except for some starting tokens. This is the same as the `StatelessExecutor` out-of-context handling.
 - Starting batch at epoch 1, this ensures that conversations (starting at zero) are below the current epoch. It also means `0` can always be used as a value guaranteed to be below the current epoch.

- Clarified comments on native metadata loading methods

LLamaToken Struct

- made `llama_backend_init` private. This is automatically called, there is no way it can correctly be used externally.
 - made `llama_token_to_piece` safe (Span instead of pointer)

- Wrapped some native functions which take (pointer, length) in function which take a `span` instead.

- Made `NativeApi` into a `static class` (it's not intended to be instantiated)
 - Moved `LLamaTokenType` enum out into a separate file
 - Made `LLamaSeqId` and `LLamaPos` into `record struct`, convenient to have equality etc

- Built by this run: https://github.com/SciSharp/LLamaSharp/actions/runs/6921572568
 - commit: `e937066420b79a757bf80e9836eb12b88420a218`
 - Rearranged paths

This reverts commit 091b8d58b3502a99b3bfbec9db457c92cc736beb, reversing
changes made to 9b2ca9cf8e.

This reverts commit b4b3ea9d99.

Just merge cuda and avx detection and change layout.

had to update binary to `b1426`

CPU Feature Detection

Based on this version: 6b73ef1201

- Minor changes to cleanup some of the compiler warnings

- Added some more comments
 - Modified `llama_tokenize` to not allocate
 - Modified `llama_tokenize_native` to take a pointer instead of an array, allowing use with no allocations
 - Removed GgmlInitParams (not used)