Stars
My self-trained AI models for photorealistic image upscaling and restoration. Built on ESRGAN, SAFMN, RealPLKSR and other architectures and trained on a manually curated high-end dataset (11,750+ r…
Suckless no dependencies CUDA/C++ port of NVIDIA's DVLT, feed it images, get a 3D point cloud + camera poses. NO python. One fast 5MB binary.
ComfyUI wrapper for Motion capture from video
TripoSplat converts a single 2D image into high-quality and variable number of 3D Gaussians, developed by TripoAI.
A LD_PRELOAD library to share CUDA VRAM weights across multiple processes using IPC.
Pixal3D image-to-3D nodes for ComfyUI - local TencentARC Pixal3D generation with textured GLB export + Windows support
Fast stackful fibers with a NUMA-aware work-stealing scheduler
Speed and samples benchmark: for all types of text to speech (TTS) models on Windows/Linux/Mac.
G-code generator for Snapmaker U1 with Full Spectrum layer blending
Generate custom gridfinity bins with AI, from photos of your tools
Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read
Fast, lossless LLM inference via dual-view diffusion decoding.
Kotlin Android app for Bambu 3D printers in Developer Mode
Box64 - Linux Userspace x86_64 Emulator with a twist, targeted at ARM64, RV64 and LoongArch Linux devices
A fast usermode x86 and x86-64 emulator for Arm64 Linux
Create real electronics with Typescript and React
A collection of agent skills for CAD, robotics and hardware design
Bitmap & tilemap generation from a single example with the help of ideas from quantum mechanics
A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.
LLM inference in C/C++
KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44x fewer params. Drop-in llama.cpp integration.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
DeepTutor: Agent-native Personalized Tutoring. https://deeptutor.info/.
Fast LLM speculative inference server for consumer hardware.