SPIRV-Cross is a practical tool and library for performing reflection on SPIR-V and disassembling SPIR-V back to high level languages.

Examples for Apple's Metal APIs (rendering and compute).

A repository where GPU applications are aggregated using a common build flow that supports multiple CUDA versions.

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

Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O

A GPU benchmark tool for evaluating GPUs and CPUs on mixed operational intensity kernels (CUDA, OpenCL, HIP, SYCL, OpenMP)

Java Virtual Machine (JVM) benchmarks to measure the energy consumption under different loads and with different available off-the-shelf applications.

Minimalistic 4D-parallelism distributed training framework for education purpose

(🚧 WIP) a course of LLM inference serving on Apple Silicon for systems engineers.

A quick analyzer for TornadoVM's profilling logs

GigaAPI is a user-space API that simplifies multi-GPU programming, bridging the gap between the capabilities of parallel GPU systems and the ability of developers to harness their full potential. T…

Model Context Protocol Servers

A simple tool that automatically clicks the "resume the conversation" link in Cursor IDE when rate limits are hit.

Distributed Triton for Parallel Systems

A collection of MCP servers.

linear time regular expression matching in Java

A visualization and analysis tool for TornadoVM bytecode execution logs that helps developers understand and optimize their applications running on TornadoVM

Inference Llama 2 in one file of pure C & one file with CUDA

Python training for business analysts and traders

Filelize is a lightweight database designed to simplify writing and reading data into human-readable files, requiring just one line of code

llama3.cuda is a pure C/CUDA implementation for Llama 3 model.

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

Fast, Flexible and Portable Structured Generation

A python program that turns an LLM, running on Ollama, into an automated researcher, which will with a single query determine focus areas to investigate, do websearches and scrape content from vari…

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

simple terminal UI for git commands