Add GPULlama3.java as model provider to run on GPUs

Author: geoand

integration-tests/gpu-llama3/pom.xml

@@ -51,7 +51,7 @@
         <dependency>
             <groupId>io.quarkiverse.langchain4j</groupId>
             <artifactId>quarkus-langchain4j-gpu-llama3-deployment</artifactId>
-            <version>${quarkus-langchain4j.version}</version>
+            <version>999-SNAPSHOT</version>
             <type>pom</type>
             <scope>test</scope>
             <exclusions>

integration-tests/gpu-llama3/src/main/resources/application.properties

@@ -3,6 +3,3 @@ quarkus.langchain4j.gpu-llama3.chat-model.model-path=/Users/orion/LLMModels/beeh
 quarkus.langchain4j.gpu-llama3.enable-integration=true
 quarkus.langchain4j.gpu-llama3.chat-model.temperature=0.7
 quarkus.langchain4j.gpu-llama3.chat-model.max-tokens=100
-
-# Configure class loading
-quarkus.class-loading.parent-first-artifacts=org.graalvm:graal-sdk,io.github.beehive-lab:gpu-llama3

integration-tests/pom.xml

@@ -128,6 +128,11 @@
                         <artifactId>quarkus-langchain4j-llama3-java</artifactId>
                         <version>999-SNAPSHOT</version>
                     </dependency>
+                  <dependency>
+                    <groupId>io.quarkiverse.langchain4j</groupId>
+                    <artifactId>quarkus-langchain4j-gpu-llama3</artifactId>
+                    <version>999-SNAPSHOT</version>
+                  </dependency>
                     <dependency>
                         <groupId>io.quarkiverse.langchain4j</groupId>
                         <artifactId>quarkus-langchain4j-mcp</artifactId>

model-providers/gpu-llama3/runtime/pom.xml

@@ -65,6 +65,16 @@
                         </configuration>
                     </execution>
                 </executions>
+              <configuration>
+                <parentFirstArtifacts>
+                  <parentFirstArtifact>org.graalvm:graal-sdk</parentFirstArtifact>
+                  <parentFirstArtifact>io.github.beehive-lab:gpu-llama3</parentFirstArtifact>
+                </parentFirstArtifacts>
+                <runnerParentFirstArtifacts>
+                  <runnerParentFirstArtifact>org.graalvm:graal-sdk</runnerParentFirstArtifact>
+                  <runnerParentFirstArtifact>io.github.beehive-lab:gpu-llama3</runnerParentFirstArtifact>
+                </runnerParentFirstArtifacts>
+              </configuration>
             </plugin>
             <plugin>
                 <artifactId>maven-compiler-plugin</artifactId>