Skip to content
View markpp's full-sized avatar
  • Aalborg University
  • Denmark

Block or report markpp

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on App…

Python 2,726 214 Updated Nov 7, 2026

A high-throughput and memory-efficient inference and serving engine for LLMs

Python 97,220 25,039 Updated Nov 19, 2026

LLM Inference Engine for Metal, CUDA and Vulkan.

Zig 2,344 548 Updated Nov 19, 2026

A local inference engine for Apple silicon, built around the model.

C++ 2,467 241 Updated Nov 17, 2026

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.

C++ 45,912 5,104 Updated Nov 18, 2026

Fast and memory-efficient classical machine learning operators

Python 604 62 Updated Oct 13, 2026

FlexGlue: Sparse-to-Dense Feature Matching and Visual Disambiguation

Python 353 18 Updated Nov 10, 2026

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.

Zig 496 41 Updated Nov 19, 2026

Code for a household crane robot

Python 201 14 Updated Nov 17, 2026

pi pod: run pi coding-agent sessions in remote sandboxes, on a server you run yourself

TypeScript 167 5 Updated Nov 19, 2026

Automatically exported from code.google.com/p/blendercam

G-code 590 143 Updated Jan 1, 2026

Flash Nvidia Jetson devices with Linux_for_Tegra (L4T) in Docker container. No SDK Manager needed

Dockerfile 6 1 Updated Sep 10, 2026

NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.

Python 8,399 1,543 Updated Nov 17, 2026

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Python 28,987 6,103 Updated Nov 19, 2026

A Blender extension for code-less generation of synthetic image datasets for computer vision

Python 28 2 Updated Oct 26, 2026

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…

Python 17 3 Updated Nov 1, 2026

ONNX-compatible LightGlue: Local Feature Matching at Light Speed. Supports TensorRT, OpenVINO

Python 829 83 Updated Jul 30, 2026

Real-time FastSAM instance segmentation on a live camera feed, with react-native-executorch and vision-camera

TypeScript 7 1 Updated Sep 17, 2026

SURE-Map: Self-Correcting Streaming Geometric Foundation Models

Python 167 7 Updated Sep 22, 2026

ViPE: Video Pose Engine for Geometric 3D Perception

Python 2,215 184 Updated Nov 5, 2026

Official implementation of Déjà View: Looping Transformers for Multi-View 3D Reconstruction

Python 560 30 Updated Nov 13, 2026

Track and extract any 3D object from video. C++/GGML convertion of Meta's sam3d PyTorch model plus a demo app

C++ 54 4 Updated Oct 19, 2026
141 15 Updated Sep 14, 2026

G-ray: Ray-Level Relative Geometric Position Encoding in Multi-View Vision Transformers under Camera Heterogeneity. Code coming soon.

24 Updated Sep 15, 2026
Python 165 13 Updated Oct 29, 2026

Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation

Python 971 79 Updated Oct 5, 2026

Automated, hardware-independent Hand-Eye Calibration for ROS2

Python 329 69 Updated Aug 20, 2026

⚡️A native, local-first alternative to Logitech Options+, written in Rust 🦀 — remap buttons, DPI, and SmartShift over HID++. No account, no telemetry.

Rust 25,923 978 Updated Nov 19, 2026

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Python 23,756 2,154 Updated Nov 19, 2026

High-performance single-GPU inference for selected model checkpoints and GPUs.

C++ 3,387 728 Updated Nov 18, 2026
Next