Recent Posts

• LLM Inference in pure Java with a GPU acceleration enabled
  by mikepapadimon 6/11/2025, 8:04:41 PM with 0 comments
• GPU-enabled Llama 3 inference in Java from scratch
  by mikepapadimon 6/2/2025, 7:40:26 AM with 0 comments
• GPULlama3.java – Llama3.java on Steroids
  by mikepapadimon 5/30/2025, 9:45:31 AM with 1 comment
• Llama Deck:CLI for running multiple language implementations of LLM inference
  by mikepapadimon 11/8/2024, 5:51:18 PM with 1 comment
• Llama3 Inference in Pure Java
  by mikepapadimon 5/18/2024, 9:35:54 AM with 0 comments
• Building libraries for LLM inference in pure modern Java
  by mikepapadimon 5/16/2024, 8:12:00 PM with 0 comments
• Java VectorAPI compatiblity with TornadoVM GPU programming framework
  by mikepapadimon 3/29/2024, 2:26:36 PM with 0 comments
• Java GPU pre/post processing with ONNX RT and TornadoVM
  by mikepapadimon 3/29/2024, 2:23:53 PM with 0 comments
• Multifaceted Memory Analysis of Java Benchmarks with NUMAProfiler and PerfUtil [pdf]
  by mikepapadimon 3/20/2024, 1:06:55 PM with 1 comment
• Ask HN: Do you know any new llama2.c implementations not mentioned in the repo
  by mikepapadimon 1/10/2024, 9:05:37 AM with 1 comment
• Llama2-shepherd a CLI tool to install multiple implementations of the llama2
  by mikepapadimon 1/4/2024, 12:24:29 PM with 4 comments
• Java and LLMs: are we there yet?
  by mikepapadimon 12/21/2023, 1:54:21 PM with 0 comments