Tensors and Dynamic neural networks in Python with strong GPU acceleration
- neural-network
- autograd
- gpu
- numpy
Repository Index
47,133 repositories indexed
1–24 of 77 · Most stars
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
The fastai deep learning library
High-performance In-browser LLM Inference Engine
A WebGL accelerated JavaScript library for training and deploying ML models.
- deep-learning
- typescript
- webgl
- javascript
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
- autodiff
- deep-learning
- machine-learning
- rust
🤖 GPU accelerated Neural networks in JavaScript for Browsers and Node.js
- neural-network
- brain
- recurrent-neural-networks
- easy-to-use
Suite of tools for deploying and training deep learning models using the JVM. Highlights include model import for keras, tensorflow, and onnx/pytorch, a modular and tiny c++ library for running math code and a java based math library on top of the core c++ library. Also includes samediff: a pytorch/tensorflow like library for running deep learn...
- java
- gpu
- deeplearning
- neural-nets
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
- tensorrt
- nvidia
- deep-learning
- inference
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model
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.
- machine-learning
- decision-trees
- gradient-boosting
- gbm
H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.
NVIDIA cuML: GPU-Accelerated Machine Learning
- machine-learning-algorithms
- machine-learning
- cuda
- gpu
Optimized primitives for collective multi-GPU communication
- communications
- cpp
- cuda
- deep-learning
Run Keras models in the browser, with GPU support using WebGL
Open-source library of optimized deep learning operations (matmul, convolution, attention) for CPUs (x64, AArch64, RISC-V) and Intel GPUs. Used by PyTorch, TensorFlow, OpenVINO, and ONNX Runtime.
- onednn
- oneapi
- performance
- cpp
Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.
- webgpu
- deep-learning
- stable-diffusion
- web-assembly
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
- pytorch
- protein-structure
- alphafold2
The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vision, Whisper speech-to-text, Stable Diffusion, tool calling, and local-network servers. Runs on your CPU, GPU, or NPU. No account, no API key, zero data leaves your device.
- privacy-first
- gguf
- llama-cpp
- local-ai
2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
- kv-cache
- llm-inference
- local-llm
- quantization