- Added disposal check into `SafeLLamaContextHandle`

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

Improved Tensor Splits

Cleaned up multiple enumeration in FixedSizeQueue

ModelParams & InferenceParams abstractions

feat: update the llama backends.

Expose some native classes

Update llama.cpp binaries to 5f631c2 and align the LlamaContext

GitHub actions

- Caching that folder, so CI only has to download it once.

- using 6.0.x instead of 7.0.x

The poc of the test is working know. Finally the problem error seems to be related with the process stopping.
Once I changed the context with today llama.cpp binaries is working OK

It solves the problem with netstandard2 (is it really netstandard2 a thing right now?)
Change context to solve problems.

5f631c2679

Fixed Mirostate Sampling