mikepapadim

llama-shepherd-cli

A CLI to manage install and configure llama inference implemenation in multiple languages

llama2.tornadovm.java

An extension to Llama2.java implementation accelerated with GPUs, using TornadoVM

collage-non-tvm-fork

Collage non-forked version for POC

vimrc

The ultimate Vim configuration (vimrc)

commitgpt

Automatically generate commit messages using ChatGPT

devoxx2024

fzf

:cherry_blossom: A command-line fuzzy finder

gpt-engineer

Specify what you want it to build, the AI asks for clarification, and then builds it.

java

Java bindings for TensorFlow

Jlama

Jlama is a pure Java implementation of a LLM inference engine.

jvm_allocation_ref

A toy application comparing primitive array allocation on heap with Panama off-heap memory segment allocation

kernl

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

Llama-2-Onnx

llama2.c

Inference Llama 2 in one file of pure C

llama2.java

Inference Llama 2 in one file of pure Java

llama3.java

Practical Llama 3 inference in Java

llamafile

Distribute and run LLMs with a single file.

llm-apps-java-spring-ai

Samples showing how to build Java applications powered by Generative AI and LLMs using Spring AI and Spring Boot.

mikepapadim

Github profile custom

mlir-tutorial

models

A collection of pre-trained, state-of-the-art models in the ONNX format

rjvm

A tiny JVM written in Rust. Learning project

sd4j

Stable diffusion pipeline in Java using ONNX Runtime

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

torchscript-to-tvm

TornadoVM

Tornado: A practical and efficient heterogeneous programming framework for managed languages

tutorials

Tutorials for creating and using ONNX models

tvm

Open deep learning compiler stack for cpu, gpu and specialized accelerators

wasmtime

A fast and secure runtime for WebAssembly