- Added new build define (`-DLLAMA_METAL_EMBED_LIBRARY=ON`) to MacOS build

fix: add cuda llava native libraries.

This reverts commit 5fda26c610.

* Add llava_binaries, update all binaries to make the test

* Llava API + LlavaTest

Preliminary

* First prototype of Load + Unit Test

* Temporary run test con branch LlavaAPI

* Disable Embed test to review the rest of the test

* Restore Embedding test

* Use BatchThread to eval image embeddings

Test Threads default value to ensure it doesn´t produce problems.

* Rename test file

* Update action versions

* Test only one method, no release embeddings

* Revert "Test only one method, no release embeddings"

This reverts commit 264e176dcc.

* Correct API call

* Only test llava related functionality

* Cuda and Cblast binaries

* Restore build policy

* Changes related with code review

* Add SafeHandles

* Set overwrite to upload-artifact@v4

* Revert to upload-artifact@v3

* revert to upload-artifact@v3

* Include llava binaries in the build

* Temporary comment

* Temporary do not remove artifacts

* Update upload version

* Remove artifacts

Fix SHA256 hash path

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

using bash expansion expression, combined with mkdir -p (--parents), allows us to create all of the directories at once.

`deps/{avx,avx2,avx512,osx-arm64,osx-x64,cu11.7.1,cu12.1.0,clblast}`
expands to: deps/avx deps/avx2 deps/avx512 deps/osx-arm64 deps/osx-x64 deps/cu11.7.1 deps/cu12.1.0 deps/clblast

I am not on my game today 🤦

GHA doesn't seem to load the value into the enviroment variable first, so the workflow always runs on master.

This results in windows users not needing to rename the DLL. This allows native llama builds to be dropped in, even on windows.

I also took the time to update the documentation, removing references to renaming the files, since the names now match.

Fixes #463

This fixes the build step: Compile (Windows) (avx512, -DLLAMA_AVX512=ON -LLAMA_AVX512_VBMI=ON -DLLAMA_AVX512_VNNI=ON)

There is a typo in the cmake command: `cmake .. -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_TESTS=OFF -DLLAMA_BUILD_EXAMPLES=OFF -DLLAMA_BUILD_SERVER=OFF -DBUILD_SHARED_LIBS=ON -DLLAMA_AVX512=ON -LLAMA_AVX512_VBMI=ON -DLLAMA_AVX512_VNNI=ON
  cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}`

-LLAMA_AVX512_VBMI
Should be
-DLLAMA_AVX512_VBMI

- Enabled more features in build process (VBMI and VNNI)
 - Added runtime checking for this features
 - Improved runtime checking to no longer require dotnet8.0

- Removed leftover metal file upload

- Removed inputs (they never worked anyway)
 - Put all deps into one final zip file

- Added `COMMON_DEFINE` env var which will contain all common defines for all platforms (experimental)