CUDA

llama.cppggml-org/llama.cpp

A C/C++ library for efficient, cross-platform LLM inference with extensive hardware support and quantization.

PyTorch - Tensors and Dynamic neural networks in Python with strong GPU accelerationpytorch/pytorch

A Python package for tensor computation with GPU acceleration and dynamic neural networks built on a tape-based autograd system.

vllmvllm-project/vllm

A high-throughput, memory-efficient inference and serving engine for large language models (LLMs).

whisper.cppggerganov/whisper.cpp

High-performance C/C++ port of OpenAI's Whisper for efficient, cross-platform speech recognition.

Bindings for many languagesggerganov/whisper.cpp

A high-performance C/C++ port of OpenAI's Whisper model for efficient, cross-platform speech recognition.

Colossal-AI - An Integrated Large-scale Model Training System with Efficient Parallelization Techniqueshpcaitech/ColossalAI

A unified deep learning system for efficient large-scale model training and inference with advanced parallelism strategies.

FAISSfacebookresearch/faiss

A library for efficient similarity search and clustering of dense vectors, scaling to billions of vectors on a single server.

DragGANXingangPan/DragGAN

Interactive point-based manipulation tool for editing GAN-generated images by dragging points to target positions.

Caffe Model ZooBVLC/caffe

A fast open framework for deep learning with a focus on expression, speed, and modularity.

OpenposeCMU-Perceptual-Computing-Lab/openpose

Real-time multi-person keypoint detection library for body, face, hands, and foot estimation.

GitHub repositoryApolloAuto/apollo

An open-source, high-performance platform for developing, testing, and deploying autonomous vehicles.

Darknetpjreddie/darknet

An open source neural network framework in C and CUDA, known for YOLO real-time object detection models.

candle-wasm-exampleshuggingface/candle

A minimalist, high-performance machine learning framework for Rust with a focus on serverless inference and GPU support.

Buzzchidiwilliams/Buzz

An offline desktop application for transcribing and translating audio/video files, live recordings, and YouTube links using OpenAI's Whisper.

lightgbmlightgbm-org/LightGBM

A fast, distributed gradient boosting framework based on decision tree algorithms for ranking, classification, and other ML tasks.

CNTK - Microsoft Cognitive ToolkitMicrosoft/CNTK

A unified deep learning toolkit for describing neural networks as computational graphs, supporting feed-forward DNNs, CNNs, and RNNs/LSTMs.

burntracel-ai/burn

A Rust-based deep learning framework and tensor library optimized for flexibility, efficiency, and cross-platform portability.

Kaldikaldi-asr/kaldi

A comprehensive open-source toolkit for speech recognition research and development.

Deeplearning4jdeeplearning4j/deeplearning4j

A comprehensive JVM-based deep learning ecosystem for building, training, and deploying models with support for model import and distributed training.

TensorRTNVIDIA/TensorRT

NVIDIA's SDK for high-performance deep learning inference optimization and deployment on NVIDIA GPUs.

cupycupy/cupy

A NumPy/SciPy-compatible array library for GPU-accelerated computing with Python, supporting NVIDIA CUDA and AMD ROCm.

Taskflowtaskflow/taskflow

A fast, expressive, and header-only C++ library for building task-parallel programs with static, dynamic, and conditional task graphs.

cudfrapidsai/cudf

A GPU-accelerated DataFrame library for tabular data processing, part of the RAPIDS data science suite.

Torch7 Cheat sheettorch/torch7

A scientific computing framework with wide support for machine learning algorithms, built around multi-dimensional tensor operations.

mistral.rsEricLBuehler/mistral.rs

A fast, flexible, and hardware-aware LLM inference engine with zero-config support for any Hugging Face model.

gocvhybridgroup/gocv

Go language bindings for OpenCV 4, enabling computer vision applications with support for CUDA, DNN, and OpenVINO.

gorgoniagorgonia/gorgonia

A library for building and evaluating mathematical expressions and neural networks in Go, with automatic differentiation and GPU support.

Chainerchainer/chainer

A flexible Python deep learning framework using define-by-run dynamic computational graphs for neural network research.

NeuralTalkkarpathy/neuraltalk2

Efficient image captioning code in Torch, using a CNN-RNN model to generate captions for images, optimized for GPU training.

leafautumnai/leaf

An open-source machine learning framework for building classical, deep, or hybrid ML applications with a focus on performance and portability.

rusttensorflow/rust

Rust language bindings for TensorFlow, providing idiomatic access to machine learning capabilities.

flashlightflashlight/flashlight

A fast, flexible C++ standalone library for machine learning with high-performance defaults and total internal modifiability.

flashlightfacebookresearch/flashlight

A fast, flexible C++ standalone library for machine learning with high-performance defaults and total internal modifiability.

yolactdbolya/yolact

A fully convolutional neural network for real-time instance segmentation, achieving high speed and accuracy on COCO.

cuMLrapidsai/cuml

A suite of GPU-accelerated machine learning algorithms with scikit-learn compatible APIs for 10-50x faster performance on large datasets.

GitHub repositoryNVIDIAGameWorks/kaolin

A PyTorch library providing GPU-accelerated tools for 3D deep learning, including differentiable rendering and geometric operations.