#Cuda
Showing 60 of 280 repositories tagged #cuda, ranked by stars
A high-throughput and memory-efficient inference and serving engine for LLMs
SGLang is a high-performance serving framework for large language models and multimodal models.
Build and run Docker containers leveraging NVIDIA GPUs
Instant neural graphics primitives: lightning fast NeRF and more
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
CUDA on non-NVIDIA GPUs
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
Open3D: A Modern Library for 3D Data Processing
Solve puzzles. Learn CUDA.
NumPy & SciPy for GPU
NumPy aware dynamic Python compiler using LLVM
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
CUDA Templates and Python DSLs for High-Performance Linear Algebra
cuDF - GPU DataFrame Library
Containers for machine learning
OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.
Modular ZK(Zero Knowledge) backend accelerated by GPU
Go package for computer vision using OpenCV 4 and beyond. Includes support for DNN, CUDA, OpenCV Contrib, and OpenVINO.
An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.
A Python framework for GPU-accelerated simulation, robotics, and machine learning.
A flexible framework of neural networks for deep learning
FlashInfer: Kernel Library for LLM Serving
A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.
Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.
cuML - RAPIDS Machine Learning Library
A PyTorch Library for Accelerating 3D Deep Learning Research
Optimized primitives for collective multi-GPU communication
Fast inference engine for Transformer models
Tengine is a lite, high performance, modular inference engine for embedded device
Lightning fast C++/CUDA neural network framework
A retargetable MLIR-based machine learning compiler and runtime toolkit.
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.
Train, inspect, edit, automate, and export 3D Gaussian Splatting scenes from a single native application.
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
Open source neural network chess engine with GPU acceleration and broad hardware support.
how to optimize some algorithm in cuda.
A GPU-powered real-time analytics storage and query engine.
HeavyDB (formerly MapD/OmniSciDB)
PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.
Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign language bindings, just Rust.
NVIDIA GPU Operator creates, configures, and manages GPUs in Kubernetes
CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.
computer vision projects | 计算机视觉相关好玩的AI项目（Python、C++、embedded system）
Pytorch domain library for recommendation systems
Apache Mahout - an environment for quickly creating scalable, performant machine learning applications.
Multi-platform high-performance compute language extension for Rust.
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
🤖 A Python library for learning and evaluating knowledge graph embeddings
A deep learning package for many-body potential energy representation and molecular dynamics
GPU Accelerated t-SNE for CUDA with Python bindings
Deep learning in Rust, with shape checked tensors and neural networks
PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
Large-scale LLM inference engine
🚀🚀🚀 A collection of some awesome public YOLO object detection series projects and the related object detection datasets.
Ultrafast serverless GPU inference, sandboxes, and background jobs
