Updated Examples

Added increment and decrement operators to `LLamaPos`

Small KV Cache Handling Improvements

Using `AddRange` in `LLamaEmbedder`

- Added `KvCacheSequenceDivide`
 - Moved count tokens/cells methods to `SafeLLamaContextHandle`

Smaller Unit Test Model

Added new file types to quantisation

Update binaries feb 2024

Disable SHA256 check

Create nuspec for OpenCL

Fix SHA256 hash path

CLBlast for linux

Only allow one build in parallel per ref

This builds CLBLAST support for linux, and makes sure to copy the
clblast shared library on both windows and linux to the artifacts.

KernelMemory EmbeddingMode bug correction

Updated download-artifact to v4

Updated compile.yml to use `Jimver/cuda-toolkit@v0.2.14`

Updated compile.yml to use `actions/upload-artifact@v4`

Updated compile.yml to use checkout v4

Swapped `GetEmbeddings` to `llama_decode`

- Modified `GetEmbeddings` method to be async

Add CLBLAST native library to native libraries build

Removed `SafeLLamaHandleBase` Constructor

Removed `IModelParams` and `IContextParams` setters.

- Also fixed `ToString()` in `SafeLLamaHandleBase`

Fix incorrect event input variable name

Fix missing library name prefix for cuda