Stars
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
Arm64 inline hooking for iOS, Android, OSX, and Linux.
Code execution utilities for Open WebUI & Ollama
Zotero is a free, easy-to-use tool to help you collect, organize, annotate, cite, and share your research sources.
Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training
Vulkan-based Gaussian Splatting viewer, and python binding
An innovative library for efficient LLM inference via low-bit quantization
Universal local privilege escalation Proof-of-Concept exploit for CVE-2024-1086, working on most Linux kernels between v5.14 and v6.6, including Debian, Ubuntu, and KernelCTF. The success rate is 9…
Full set of AppArmor profiles (~ 1500 profiles)
Production-grade 3D gaussian splatting with CPU/GPU support for Windows, Mac and Linux 🚀
3D Gaussian Splatting Renderer implemented in WebGPU (WGPU) and Rust
A 3d gaussian splatting renderer in C++ and OpenGL
A compute shader implementation of the OneSweep sorting algorithm.
GPU Radix Sort implemented in Vulkan and GLSL.
A cross-platform, high performance renderer for Gaussian Splatting using Vulkan Compute. Supports Windows, Linux, macOS, iOS, and visionOS
Volumetric Display using an Acoustically Trapped Particle
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
CLI platform to experiment with codegen. Precursor to: https://lovable.dev
Instruct-tune LLaMA on consumer hardware
Generate 3D objects conditioned on text or images
ILLIXR-docker is a GPU-enabled Docker container that provides a development-ready environment for ILLIXR
A tool to bypass Minecraft Java Edition model limits by baking vertex data into texture.
PyTorch package for the discrete VAE used for DALL·E.