CUDA Templates and Python DSLs for High-Performance Linear Algebra

A controlled concurrency testing framework for the JVM

the WebAssembly partial evaluator

The best ChatGPT that $100 can buy.

Performance Optimizer Observation Platform

Hacking GraalVM Espresso - Abusing Continuation API to Make ROP-like Attack

Implementation of interference of large language models in Java using the Vector-API.

Implementation of interference of large language models in Java using the Vector-API.

A template project for Truffle languages using a tree-sitter parser

GPU-accelerated Llama3.java inference in pure Java using TornadoVM.

C++ Implementation of Algorithms (aka. Spaghetti Source)

Practical Llama 3 inference in Java

llama3 inference in pure luajit ffi

👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.

DevoxxGenie is a plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code.

JTokkit is a Java tokenizer library designed for use with OpenAI models.

A Java port of Andrej Karpathy‘s llm.c.

A BM25 Java implementation using streams, stop words and stemming.

Jlama is a modern LLM inference engine for Java

Quarkus Langchain4j extension

Llama3.java Inference engine with OpenAI Chat Completion REST API/

Official inference framework for 1-bit LLMs

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

JVM agent that track access to off-heap memory via Unsafe class (BETA)

Picocli is a modern framework for building powerful, user-friendly, GraalVM-enabled command line apps with ease. It supports colors, autocompletion, subcommands, and more. In 1 source file so apps …

Native JVM WebAssembly runtime

Bringing heterogenous hardware acceleration to Kotlin machine learning