Originally from these PRs:
 - https://github.com/SciSharp/LLamaSharp/pull/263
 - https://github.com/SciSharp/LLamaSharp/pull/259

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

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`).

Major llama.cpp API Change

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

- Replaced all binaries

- params contains a list of loras, instead of just one

- Added a "spinner" to the `StatelessModeExecute` demo, which spins while waiting for the next token (demonstrating that it's not blocked).

- Removed unused `AddRangeSpan` extension

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

Add GGUF support

- Made all the mechanics of grammar parsing (GBNFGrammarParser, ParseState) internal. Just call `Grammar.Parse("whatever")`.
 - Added a `GrammarRule` class which validates elements on construction (this allows constructing grammar without parsing GBNF).
   - It should be impossible for a `GrammarRule` to represent an invalid rule.

- 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

- Renamed `DictionaryExtensions` to `KeyValuePairExtensions`, since nothing in that file extends dictionary any more!