diff --git a/LLama.KernelMemory/LLamaSharp.KernelMemory.csproj b/LLama.KernelMemory/LLamaSharp.KernelMemory.csproj
index 175a4f280..cad114341 100644
--- a/LLama.KernelMemory/LLamaSharp.KernelMemory.csproj
+++ b/LLama.KernelMemory/LLamaSharp.KernelMemory.csproj
@@ -4,7 +4,7 @@
     <TargetFrameworks>net8.0</TargetFrameworks>
     <ImplicitUsings>enable</ImplicitUsings>
     <Nullable>enable</Nullable>
-    <Version>0.13.0</Version>
+    <Version>0.14.0</Version>
     <Authors>Xbotter</Authors>
     <Company>SciSharp STACK</Company>
     <GeneratePackageOnBuild>true</GeneratePackageOnBuild>
@@ -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>
-      v0.12.0 released with v0.12.0 of LLamaSharp.
+      v0.14.0 released with v0.14.0 of LLamaSharp.
     </PackageReleaseNotes>
     <PackageLicenseExpression>MIT</PackageLicenseExpression>
     <PackageOutputPath>packages</PackageOutputPath>
diff --git a/LLama.SemanticKernel/LLamaSharp.SemanticKernel.csproj b/LLama.SemanticKernel/LLamaSharp.SemanticKernel.csproj
index e04484dd1..c513f4453 100644
--- a/LLama.SemanticKernel/LLamaSharp.SemanticKernel.csproj
+++ b/LLama.SemanticKernel/LLamaSharp.SemanticKernel.csproj
@@ -10,7 +10,7 @@
 		<ImplicitUsings>enable</ImplicitUsings>
 		<Nullable>enable</Nullable>
 
-		<Version>0.13.0</Version>
+		<Version>0.14.0</Version>
 		<Authors>Tim Miller, Xbotter</Authors>
 		<Company>SciSharp STACK</Company>
 		<GeneratePackageOnBuild>true</GeneratePackageOnBuild>
@@ -23,7 +23,7 @@
 			The integration of LLamaSharp and Microsoft semantic-kernel.
 		</Description>
 		<PackageReleaseNotes>
-			v0.12.0 released with v0.12.0 of LLamaSharp.
+			v0.14.0 released with v0.14.0 of LLamaSharp.
 		</PackageReleaseNotes>
 		<PackageLicenseExpression>MIT</PackageLicenseExpression>
 		<PackageOutputPath>packages</PackageOutputPath>
diff --git a/LLama/LLamaSharp.csproj b/LLama/LLamaSharp.csproj
index 1562e8434..272c81e37 100644
--- a/LLama/LLamaSharp.csproj
+++ b/LLama/LLamaSharp.csproj
@@ -7,7 +7,7 @@
     <Platforms>AnyCPU;x64;Arm64</Platforms>
     <AllowUnsafeBlocks>True</AllowUnsafeBlocks>
 
-    <Version>0.13.0</Version>
+    <Version>0.14.0</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 include better support for LLama3 tokenization.
+      Updated llama.cpp version to include better support for gemma.
     </PackageReleaseNotes>
     <PackageLicenseExpression>MIT</PackageLicenseExpression>
     <PackageOutputPath>packages</PackageOutputPath>
diff --git a/README.md b/README.md
index 31b64bb7f..e065a2eb3 100644
--- a/README.md
+++ b/README.md
@@ -98,7 +98,7 @@ PM> Install-Package LLamaSharp
    - [`LLamaSharp.Backend.Cpu`](https://www.nuget.org/packages/LLamaSharp.Backend.Cpu): Pure CPU for Windows, Linux & Mac. Metal (GPU) support for Mac.
    - [`LLamaSharp.Backend.Cuda11`](https://www.nuget.org/packages/LLamaSharp.Backend.Cuda11): CUDA 11 for Windows & Linux.
    - [`LLamaSharp.Backend.Cuda12`](https://www.nuget.org/packages/LLamaSharp.Backend.Cuda12): CUDA 12 for Windows & Linux.
-   - [`LLamaSharp.Backend.OpenCL`](https://www.nuget.org/packages/LLamaSharp.Backend.OpenCL): OpenCL for Windows & Linux.
+   - [`LLamaSharp.Backend.Vulkan`](https://www.nuget.org/packages/LLamaSharp.Backend.Vulkan): Vulkan for Windows & Linux.
 
 3. (optional) For [Microsoft semantic-kernel](https://github.com/microsoft/semantic-kernel) integration, install the [LLamaSharp.semantic-kernel](https://www.nuget.org/packages/LLamaSharp.semantic-kernel) package.
 4. (optional) To enable RAG support, install the [LLamaSharp.kernel-memory](https://www.nuget.org/packages/LLamaSharp.kernel-memory) package (this package only supports `net6.0` or higher yet), which is based on [Microsoft kernel-memory](https://github.com/microsoft/kernel-memory) integration.
@@ -251,6 +251,7 @@ If you want to compile llama.cpp yourself you **must** use the exact commit ID l
 | v0.11.1, v0.11.2 | [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) |
 | v0.12.0 | LLama3 | [`a743d76`](https://github.com/ggerganov/llama.cpp/tree/a743d76a01f23038b2c85af1e9048ee836767b44) |
 | v0.13.0 | | [`1debe72`](https://github.com/ggerganov/llama.cpp/tree/1debe72737ea131cb52975da3d53ed3a835df3a6) |
+| v0.14.0 | Gemma2 | [`368645698ab648e390dcd7c00a2bf60efa654f57`](https://github.com/ggerganov/llama.cpp/tree/368645698ab648e390dcd7c00a2bf60efa654f57) |
 
 ## License