* Updated binaries, using [this build](https://github.com/SciSharp/LLamaSharp/actions/runs/8654672719/job/23733195669) for llama.cpp commit `f7001ccc5aa359fcf41bba19d1c99c3d25c9bcc7`.

 - Added all new functions.
 - Moved some functions (e.g. `SafeLlamaModelHandle` specific functions) into `SafeLlamaModelHandle.cs`
 - Exposed tokens on `SafeLlamaModelHandle` and `LLamaWeights` through a `Tokens` property. As new special tokens are added in the future they can be added here.
 - Changed all token properties to return nullable tokens, to handle some models not having some tokens.
 - Fixed `DefaultSamplingPipeline` to handle no newline token in some models.

* Moved native methods to more specific locations.

 - Context specific things have been moved into `SafeLLamaContextHandle.cs` and made private - they're exposed through C# properties and methods already.
 - Checking that GPU layer count is zero if GPU offload is not supported.
 - Moved methods for creating default structs (`llama_model_quantize_default_params` and `llama_context_default_params`) into relevant structs.

* Removed exception if `GpuLayerCount > 0` when GPU is not supported.

* - Added low level wrapper methods for new per-sequence state load/save in `SafeLLamaContextHandle`
 - Added high level wrapper methods (save/load with `State` object or memory mapped file) in `LLamaContext`
 - Moved native methods for per-sequence state load/save into `SafeLLamaContextHandle`

* Added update and defrag methods for KV cache in `SafeLLamaContextHandle`

* Updated submodule to `f7001ccc5aa359fcf41bba19d1c99c3d25c9bcc7`

* Passing the sequence ID when saving a single sequence state

Conversations can be "forked", to create a copy of a conversation at a given point. This allows e.g. prompting a conversation with a system prefix just once and then forking it again and again for each individual conversation. Conversations can also be "rewound" to an earlier state.

Added two new examples, demonstrating forking and rewinding.

- Added `logits_i` argument to `Context.ApplyPenalty`
 - Added a new exception type for `llama_decode` return code

- Added a `Sample` method to `LLamaContext` which uses a custom pipeline
 - Modified all executors to use the custom pipeline if it exists

FixedSizeQueue:
 - Enqueue would always stop one short of filling the capacity
 - Fill would only _replace_ existing items. It was only used in a place where there were not existing items! Removed the method entirely.

LLamaGrammarElement:
 - Converted into a `record` struct, removed all of the (now unnecessary) equality stuff.

- Cleaned up comments in implementations of `IInferenceParams`
 - Removed default values for all parameters in `LLamaContext.Sample` - they're never used and probably _shouldn't_ ever be used

had to update binary to `b1426`

- Passing `ILogger` into executors

# Conflicts:
#	LLama.Web/Common/ModelOptions.cs
#	LLama.Web/Services/ConnectionSessionService.cs
#	LLama/LLamaStatelessExecutor.cs
#	LLama/LLamaWeights.cs

- Just convert it to a `string`, nice and simple
 - Write the bytes to a `Span<byte>` no allocations
 - Write the chars to a `StringBuilder` potentially no allocations

- Minor changes to cleanup some of the compiler warnings

- Deleted `NativeInfo` (internal class, not used anywhere)

- Removed some unnecessary `ToArray` calls
 - Initial pass on LLamaStatelessExecutor, the context overflow management is broken but I think I found where it's ported from

- Integrated grammar into sampling
 - Added a test for the grammar sampling

The biggest single change is renaming `LLamaModel` to `LLamaContext`

Fix serialization error due to NaN

- Also refactored it to return an `int[]` instead of an `IEnumerable<int>`, solving the "multiple enumeration" problems at the source!