fix: add cuda llava native libraries.

.github/workflows/compile.yml

@@ -370,7 +370,7 @@ jobs:
           cp artifacts/llava-bin-win-cublas-cu11.7.1-x64.dll/llava_shared.dll    deps/cu11.7.1/llava_shared.dll
 
           cp artifacts/llama-bin-linux-cublas-cu11.7.1-x64.so/libllama.so deps/cu11.7.1/libllama.so
-          cp artifacts/llava-bin-linux-cublas-cu11.7.1-x64.so/libllava_shared.so deps/cu11.7.1/libllama_shared.so
+          cp artifacts/llava-bin-linux-cublas-cu11.7.1-x64.so/libllava_shared.so deps/cu11.7.1/libllava_shared.so
           
           cp artifacts/llama-bin-win-cublas-cu12.1.0-x64.dll/llama.dll    deps/cu12.1.0/llama.dll
           cp artifacts/llava-bin-win-cublas-cu12.1.0-x64.dll/llava_shared.dll    deps/cu12.1.0/llava_shared.dll

LLama.Examples/Examples/LlavaInteractiveModeExecute.cs

@@ -22,6 +22,7 @@ namespace LLama.Examples.Examples
             {
                 ContextSize = 4096,
                 Seed = 1337,
+                GpuLayerCount = 10
             };
             using var model = LLamaWeights.LoadFromFile(parameters);
             using var context = model.CreateContext(parameters);

LLama/LLamaSharp.Runtime.targets

@@ -84,6 +84,15 @@
         <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
         <Link>runtimes/win-x64/native/avx512/llava_shared.dll</Link>
       </None>
+      <None Include="$(MSBuildThisFileDirectory)runtimes/deps/cu11.7.1/llava_shared.dll">
+        <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
+        <Link>runtimes/win-x64/native/cuda11/llava_shared.dll</Link>
+      </None>
+      <None Include="$(MSBuildThisFileDirectory)runtimes/deps/cu12.1.0/llava_shared.dll">
+        <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
+        <Link>runtimes/win-x64/native/cuda12/llava_shared.dll</Link>
+      </None>
+      
 
       <None Include="$(MSBuildThisFileDirectory)runtimes/deps/libllava_shared.so">
         <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
@@ -101,6 +110,14 @@
         <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
         <Link>runtimes/linux-x64/native/avx512/libllava_shared.so</Link>
       </None>
+      <None Include="$(MSBuildThisFileDirectory)runtimes/deps/cu11.7.1/libllava_shared.so">
+        <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
+        <Link>runtimes/linux-x64/native/cuda11/libllava_shared.so</Link>
+      </None>
+      <None Include="$(MSBuildThisFileDirectory)runtimes/deps/cu12.1.0/libllava_shared.so">
+        <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
+        <Link>runtimes/linux-x64/native/cuda12/libllava_shared.so</Link>
+      </None>
 
       <None Include="$(MSBuildThisFileDirectory)runtimes/deps/osx-arm64/libllava_shared.dylib">
         <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>

README.md

@@ -242,7 +242,7 @@ If you want to compile llama.cpp yourself you **must** use the exact commit ID l
 | v0.8.1 | | [`e937066`](https://github.com/ggerganov/llama.cpp/commit/e937066420b79a757bf80e9836eb12b88420a218) |
 | v0.9.0, v0.9.1 | [Mixtral-8x7B](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF) | [`9fb13f9`](https://github.com/ggerganov/llama.cpp/blob/9fb13f95840c722ad419f390dc8a9c86080a3700) |
 | v0.10.0 | [Phi2](https://huggingface.co/TheBloke/phi-2-GGUF) | [`d71ac90`](https://github.com/ggerganov/llama.cpp/tree/d71ac90985854b0905e1abba778e407e17f9f887) |
-| v0.11.0 | [LLaVA-v1.6](https://huggingface.co/ShadowBeast/llava-v1.6-mistral-7b-Q5_K_S-GGUF), [Phi2](https://huggingface.co/TheBloke/phi-2-GGUF)| [`3ab8b3a`](https://github.com/ggerganov/llama.cpp/tree/3ab8b3a92ede46df88bc5a2dfca3777de4a2b2b6) |
+| v0.11.0 | [LLaVA-v1.5](https://hf-mirror.com/jartine/llava-v1.5-7B-GGUF/blob/main/llava-v1.5-7b-mmproj-Q4_0.gguf), [Phi2](https://huggingface.co/TheBloke/phi-2-GGUF)| [`3ab8b3a`](https://github.com/ggerganov/llama.cpp/tree/3ab8b3a92ede46df88bc5a2dfca3777de4a2b2b6) |
 
 ## License