Submissions by mikepapadim

GPU-enabled Llama 3 inference in Java from scratch

GPULlama3.java – Llama3.java on Steroids

Llama Deck:CLI for running multiple language implementations of LLM inference

Llama3 Inference in Pure Java

Building libraries for LLM inference in pure modern Java

Java VectorAPI compatiblity with TornadoVM GPU programming framework

Java GPU pre/post processing with ONNX RT and TornadoVM

Multifaceted Memory Analysis of Java Benchmarks with NUMAProfiler and PerfUtil [pdf]

Llama2-shepherd a CLI tool to install multiple implementations of the llama2

Java and LLMs: are we there yet?