* 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 264e176dccc9cd0be318b800ae5e102a4635d01c.
* 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
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
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
jlsantiago
Rinne