Should fix the extreme speed loss.

- Removed all `record struct` uses in native code
 - Removed usage of `readonly` in native structs

Minor fix:
 - Added sequential layout to `LLamaModelQuantizeParams`

had to update binary to `b1426`

Multi GPU

RoundTrip Tokenization Errors

- `AntipromptProcessor` accepts chunks of text and returns a value indicating if any antiprompt has been detected.
 - `StreamingTokenDecoder` decodes tokens into text, maintaining some internal state to handle single characters which are encoded as multiple tokens.

Added tests for these classes and updated StatelessExecutor to use them.

Removed most DeTokenize methods, marked the rest as obsolete (should always use a `StreamingTokenDecoder`).

- Built a new (hacky) `Detokenize` method which handles this

Co-authored-by: Martin Evans <martindevans@gmail.com>

Co-authored-by: Martin Evans <martindevans@gmail.com>

Co-authored-by: Martin Evans <martindevans@gmail.com>

Co-authored-by: Martin Evans <martindevans@gmail.com>

Co-authored-by: Martin Evans <martindevans@gmail.com>

- Passing `ILogger` into executors

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

Major llama.cpp API Change

- Fixed stateless executor out-of-context handling
 - Fixed token tests

- Added ifdef to remove `Deconstruct` extension on everything except `NETSTANDARD2_0`

- Covered text transforms
 - Removed unnecessary non-async transforms