Big credit to @vaiju1981 for new features:

• Now with support for Gemma 3
• Update to llama.cpp b4916
• Re-ranking and chat-template support!

This major version updates from b3534 to the newest available llama.cpp version b4831.

• Huge credit to @vaiju1981 for enabling this update
• Credit to @glebashnik for exposing a function to convert json schemas to grammars

This version is a minor fix for problems with the pre-built shared libraries on Linux x86_64.

Version 3.4.0

Credit goes to @shuttie for adding CUDA support on Linux x86_64 with this version.

Upgrade to latest llama.cpp version b3534

• Include GGML backend in text log
• Update to llama.cpp b3008

Logging Re-Implementation (see #66)

• Re-adds logging callbacks via LlamaModel#setLogger(LogFormat, BiConsumer<LogLevel, String>)
• Removes dis-functional ModelParameters#setLogDirectory(String), ModelParameters#setDisableLog(boolean), andModelParameters#setLogFormat(LogFormat)

• Adds chat template support (credit to @lesters #64)
• Updates to llama.cpp b2969
• Adds explicit Phi-3 128k support

Changes:

• Updates to llama.cpp b2885
• Fixes #62 (generation can now be canceled)
• Fixes macos x64 shared libraries

API changes:

• LlamaModel.Output is now LlamaOutput
• LlamaIterator is now public, was private LlamaModel.Iterator previously

Upgrade to llama.cpp b2797

• Adds explicit support for Phi-3
• Adds flash attention
• Fixes #54