Top Repositories
ComfyUI support for DepthAnything V3 model
Sample viewer implementing several rendering methods for 3D gaussians using Vulkan API
Automatically benchmark and optimize attention in diffusion models. 1.5-2x speedup on RTX 4090.
LLM inference in C/C++
Repositories
62No description provided.
ComfyUI support for DepthAnything V3 model
Sample viewer implementing several rendering methods for 3D gaussians using Vulkan API
Automatically benchmark and optimize attention in diffusion models. 1.5-2x speedup on RTX 4090.
LLM inference in C/C++
Fast kernel library for Diffusion inference with multiple compute backends.
🌊 Images to → 3D Parallax effect video. A free and open source ImmersityAI alternative
High-performance FlashAttention-2 for AMD, Intel, and Apple GPUs. Drop-in replacement for PyTorch SDPA. Triton backend for ROCm (MI300X, RDNA3), Vulkan backend for consumer GPUs. No CUDA required.
A Cross-Platform Backend for High-Performance Sparse Convolutions
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm
Python/Raspberry Pi example with DFRobot SEN0177 PM2.5 laser dust sensor
Official implementation of "Depth Anything in 360°: Towards Scale Invariance in the Wild".
LichtFeld Studio: Where reality and the digital world blend.
No description provided.
The open source coding agent.
A high-performance Gaussian Splatting format conversion library that supports lossless conversion between multiple mainstream formats.
Copilot Chat extension for VS Code
Misc; latest version of waifu2x; 2D video to stereo 3D video conversion
No description provided.
Access to Anthropic's safety-first language model APIs via Go
The glamourous AI coding agent for your favourite terminal 💘
This custom_node for ComfyUI adds one-click "Virtual VRAM" for any GGUF UNet and CLIP loader, managing the offload of layers to DRAM or VRAM to maximize the latent space of your card. Also includes nodes for directly loading entire components (UNet, CLIP, VAE) onto the device you choose. Includes 16 examples covering common use cases.
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
Multi-protocol control & translation software (ArtNet, MIDI, OSC, sACN, ...)
Hackable and optimized Transformers building blocks, supporting a composable construction.
🌍 WorldGen - Generate Any 3D Scene in Seconds
A Go (golang) library wrapping microsoft/onnxruntime.
Chrome Extension - GitHub PR review monitor - List of PRs requiring your attention at your fingertips
Main package repository for production Wolfi images