Stars
A high-throughput and memory-efficient inference and serving engine for LLMs
A Prometheus exporter for Celery metrics
Lightweight server monitoring hub with historical data, docker stats, and alerts.
RAG that intelligently adapts to your use case, data, and queries
WordPress, Git-ified. This repository is just a mirror of the WordPress subversion repository. Please do not send pull requests. Submit pull requests to https://github.com/WordPress/wordpress-devel…
Flash OS images to SD cards & USB drives, safely and easily.
Наша попытка улучшить интерфейс лмски Центрального Университета путем создания расширения. Этот репозиторий содержит расширение для chromium-based и firefox браузеров
Implementation of Nougat Neural Optical Understanding for Academic Documents
MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis
[SIGGRAPH 2024] Official PyTorch Implementation of "BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometry".
[IV 2025, Oral] Official code of "LiDPM: Rethinking Point Diffusion for Lidar Scene Completion"
[NeurIPS'24 Spotlight] Text2CAD: Generating Sequential CAD Designs from Beginner-to-Expert Level Text Prompts
Data, tools, and documentation of the Fusion 360 Gallery Dataset
cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning
This is the official implementation of "LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels" (Accepted at CVPR 2024).
WebGL point cloud viewer for large datasets
Distribute and run LLMs with a single file.
Consul is a distributed, highly available, and data center aware solution to connect and configure applications across dynamic, distributed infrastructure.
A tool for secrets management, encryption as a service, and privileged access management
Terraform enables you to safely and predictably create, change, and improve infrastructure. It is a source-available tool that codifies APIs into declarative configuration files that can be shared …
Nomad is an easy-to-use, flexible, and performant workload orchestrator that can deploy a mix of microservice, batch, containerized, and non-containerized applications. Nomad is easy to operate and…
[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.
Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
official code of “OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding”
Automatic tiling window manager for macOS à la xmonad.
Made for publishing additional materials for my acticles and videos