Merge pull request #94 from beehive-lab/release/0.3.2

Release 0.3.2

Author: mikepapadim

CHANGELOG.md

@@ -2,6 +2,18 @@
 
 All notable changes to GPULlama3.java will be documented in this file.
 
+## [0.3.2] - 2025-12-18
+
+### Model Support
+
+- [models] Support for IBM Granite Models 3.2, 3.3 & 4.0 with FP16 and Q8 ([#92](https://github.com/beehive-lab/GPULlama3.java/pull/92))
+
+### Other Changes
+
+- [docs] Update docs to use SDKMAN! and point to TornadoVM 2.2.0 ([#93](https://github.com/beehive-lab/GPULlama3.java/pull/93))
+- Add JBang catalog and local usage examples to README.md ([#91](https://github.com/beehive-lab/GPULlama3.java/pull/91))
+- Add `jbang` script and configuration to make easy to run ([#90](https://github.com/beehive-lab/GPULlama3.java/pull/90))
+
 ## [0.3.1] - 2025-12-11
 
 ### Model Support

CITATION.cff

@@ -15,6 +15,6 @@ authors:
   given-names: "Christos"
 title: "GPULlama3.java"
 license: MIT License
-version: 0.3.1
-date-released: 2025-12-11
+version: 0.3.2
+date-released: 2025-12-18
 url: "https://github.com/beehive-lab/GPULlama3.java"

README.md

@@ -133,7 +133,7 @@ You can add **GPULlama3.java** directly to your Maven project by including the f
 <dependency>
     <groupId>io.github.beehive-lab</groupId>
     <artifactId>gpu-llama3</artifactId>
-    <version>0.3.1</version>
+    <version>0.3.2</version>
 </dependency>
 ```
 

pom.xml

@@ -7,7 +7,7 @@
         <!-- Use your verified namespace -->
         <groupId>io.github.beehive-lab</groupId>
         <artifactId>gpu-llama3</artifactId>
-        <version>0.3.2-dev</version> <!-- release version (no -SNAPSHOT) -->
+        <version>0.3.2</version> <!-- release version (no -SNAPSHOT) -->
 
         <name>GPU Llama3</name>
         <description>GPU-accelerated LLaMA3 inference using TornadoVM</description>