Merge pull request #947 from martindevans/v0.17.0

V0.17.0 Release

Author: martindevans

LLama.KernelMemory/LLamaSharp.KernelMemory.csproj

@@ -17,7 +17,7 @@
       The integration of LLamaSharp and Microsoft kernel-memory. It could make it easy to support document search for LLamaSharp model inference.
     </Description>
     <PackageReleaseNotes>
-      v0.16.0 released with v0.16.0 of LLamaSharp.
+      v0.17.0 released with v0.17.0 of LLamaSharp.
     </PackageReleaseNotes>
     <PackageLicenseExpression>MIT</PackageLicenseExpression>
     <PackageOutputPath>packages</PackageOutputPath>

LLama.SemanticKernel/LLamaSharp.SemanticKernel.csproj

@@ -23,7 +23,7 @@
 			The integration of LLamaSharp and Microsoft semantic-kernel.
 		</Description>
 		<PackageReleaseNotes>
-			v0.16.0 released with v0.16.0 of LLamaSharp.
+			v0.17.0 released with v0.17.0 of LLamaSharp.
 		</PackageReleaseNotes>
 		<PackageLicenseExpression>MIT</PackageLicenseExpression>
 		<PackageOutputPath>packages</PackageOutputPath>

LLama.Web/LLama.Web.csproj

@@ -15,7 +15,7 @@
   </ItemGroup>
 
   <ItemGroup>
-    <PackageReference Include="Microsoft.AspNetCore.Mvc.Razor.RuntimeCompilation" Version="8.0.8" />
+    <PackageReference Include="Microsoft.AspNetCore.Mvc.Razor.RuntimeCompilation" Version="8.0.10" />
     <PackageReference Include="System.Linq.Async" Version="6.0.1" />
   </ItemGroup>
 

LLama/LLamaSharp.csproj

@@ -7,7 +7,7 @@
     <Platforms>AnyCPU;x64;Arm64</Platforms>
     <AllowUnsafeBlocks>True</AllowUnsafeBlocks>
 
-    <Version>0.16.0</Version>
+    <Version>0.17.0</Version>
     <Authors>Rinne, Martin Evans, jlsantiago and all the other contributors in https://github.com/SciSharp/LLamaSharp/graphs/contributors.</Authors>
     <Company>SciSharp STACK</Company>
     <GeneratePackageOnBuild>true</GeneratePackageOnBuild>
@@ -22,7 +22,7 @@
       With the higher-level APIs and RAG support, it's convenient to deploy LLM (Large Language Model) in your application with LLamaSharp.
     </Description>
     <PackageReleaseNotes>
-        Updated llama.cpp version to 11b84eb4578864827afcf956db5b571003f18180
+        Updated llama.cpp version to c35e586ea57221844442c65a1172498c54971cb0
     </PackageReleaseNotes>
     <PackageLicenseExpression>MIT</PackageLicenseExpression>
     <PackageOutputPath>packages</PackageOutputPath>

README.md

@@ -254,6 +254,7 @@ If you want to compile llama.cpp yourself you **must** use the exact commit ID l
 | v0.14.0 | Gemma2 | [`36864569`](https://github.com/ggerganov/llama.cpp/tree/368645698ab648e390dcd7c00a2bf60efa654f57) |
 | v0.15.0 | LLama3.1 | [`345c8c0c`](https://github.com/ggerganov/llama.cpp/tree/345c8c0c87a97c1595f9c8b14833d531c8c7d8df) |
 | v0.16.0 |  | [`11b84eb4`](https://github.com/ggerganov/llama.cpp/tree/11b84eb4578864827afcf956db5b571003f18180) |
+| v0.17.0 |  | [`c35e586e`](https://github.com/ggerganov/llama.cpp/tree/c35e586ea57221844442c65a1172498c54971cb0) |
 
 ## License