-
Aalborg University
- Denmark
Stars
LLM Inference Engine for Metal, CUDA and Vulkan.
A local inference engine for Apple silicon, built around the model.
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
Fast and memory-efficient classical machine learning operators
FlexGlue: Sparse-to-Dense Feature Matching and Visual Disambiguation
Sushi engine runs very high quality quant model in Apple Silicon, using both STQ and EXL3 format with special tuning technology to achieve frontier sub 4 bits compression.
pi pod: run pi coding-agent sessions in remote sandboxes, on a server you run yourself
Automatically exported from code.google.com/p/blendercam
Flash Nvidia Jetson devices with Linux_for_Tegra (L4T) in Docker container. No SDK Manager needed
NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
A Blender extension for code-less generation of synthetic image datasets for computer vision
Eulerian Video Magnification in hand-written CUDA: up to 1,650x faster than the NumPy baseline (motion pipeline, half precision, compute-only on an RTX 3090). Five more backends (Metal, Vulkan, Ope…
fabio-sim / LightGlue-ONNX
Forked from cvg/LightGlueONNX-compatible LightGlue: Local Feature Matching at Light Speed. Supports TensorRT, OpenVINO
Real-time FastSAM instance segmentation on a live camera feed, with react-native-executorch and vision-camera
SURE-Map: Self-Correcting Streaming Geometric Foundation Models
ViPE: Video Pose Engine for Geometric 3D Perception
Official implementation of Déjà View: Looping Transformers for Multi-View 3D Reconstruction
Track and extract any 3D object from video. C++/GGML convertion of Meta's sam3d PyTorch model plus a demo app
G-ray: Ray-Level Relative Geometric Position Encoding in Multi-View Vision Transformers under Camera Heterogeneity. Code coming soon.
Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation
Automated, hardware-independent Hand-Eye Calibration for ROS2
⚡️A native, local-first alternative to Logitech Options+, written in Rust 🦀 — remap buttons, DPI, and SmartShift over HID++. No account, no telemetry.
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
High-performance single-GPU inference for selected model checkpoints and GPUs.
Nativ is an open-source local AI app for Mac. It runs open AI models on Apple Silicon, and nothing leaves your Mac.