MinP Sampler

- 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

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

This reverts commit b4b3ea9d99.

Just merge cuda and avx detection and change layout.

- 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

- `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

- Replaced all binaries

CPU Feature Detection

* Added the low level bindings to beam search.

- Minimal amount of characters converted
   - Allocation free
 - Added `TokensToSpan` to `SafeLlamaModelHandle` which converts as many tokens as possible into a character span
   - Allocation free