Updating the GpuLayerCount to mirror the Python Port of Llama.cpp

LLama/Extensions/IModelParamsExtensions.cs

@@ -25,6 +25,8 @@ public static class IModelParamsExtensions
             throw new NotSupportedException("'UseMemoryLock' is not supported (llama_mlock_supported() == false)");
         if (@params.UseMemorymap && !NativeApi.llama_mmap_supported())
             throw new NotSupportedException("'UseMemorymap' is not supported (llama_mmap_supported() == false)");
+        if (@params.GpuLayerCount < 0)
+            @params.GpuLayerCount = int.MaxValue;
 
         var disposer = new GroupDisposable();
 

LLama/LLamaSharp.csproj

@@ -1,6 +1,6 @@
 <Project Sdk="Microsoft.NET.Sdk">
   <PropertyGroup>
-    <TargetFrameworks>netstandard2.0;net6.0;net7.0;net8.0</TargetFrameworks>
+    <TargetFrameworks>netstandard2.0;net6.0;net7.0</TargetFrameworks>
     <RootNamespace>LLama</RootNamespace>
     <Nullable>enable</Nullable>
     <LangVersion>10</LangVersion>