awesome-repositories.com

Entdecke die besten Open-Source-Repositories mit KI-gestützter Suche.

EntdeckenKuratierte SuchenBlogSitemap
ProjektÜber unsPresseMCP-Server
RechtlichesDatenschutzAGB
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
awesome-repositories.comBlog
Kategorien

34 Repos

Awesome GitHub RepositoriesGPU Acceleration Libraries

Libraries and packages for offloading intensive computations to graphics processing units.

Distinguishing note: Focuses on GPU-specific acceleration setup.

Explore 34 awesome GitHub repositories matching devops & infrastructure · GPU Acceleration Libraries. Refine with filters or upvote what's useful.

Awesome GPU Acceleration Libraries GitHub Repositories

Finde die besten Repos mit KI.Wir suchen mit KI nach den am besten passenden Repositories.
  • jax-ml/jaxAvatar von jax-ml

    jax-ml/jax

    35,828Auf GitHub ansehen↗

    This project is a high-performance numerical computing library designed for large-scale scientific and machine learning workloads. It functions as an automatic differentiation framework and a just-in-time compilation engine, transforming high-level Python code into optimized machine instructions. By enforcing pure functional programming patterns and immutable array semantics, the library ensures that mathematical functions remain compatible with automated graph transformations and symbolic differentiation. The platform distinguishes itself through its distributed array computing capabilities,

    Simplifies setup for running intensive computations on compatible graphics processing units.

    Pythonjax
    Auf GitHub ansehen↗35,828
  • dmlc/xgboostAvatar von dmlc

    dmlc/xgboost

    28,471Auf GitHub ansehen↗

    XGBoost is a distributed machine learning library for implementing scalable gradient boosting decision trees used for regression, classification, and ranking. It functions as a predictive model framework and a cross-language toolkit, providing a core implementation with native bindings for Python, R, Java, Scala, and C++. The system is designed as a GPU-accelerated library that utilizes CUDA and NCCL to speed up the training of decision tree ensembles. It operates as a distributed framework capable of scaling training and prediction across multi-node clusters and GPU environments to process m

    Utilizes CUDA and NCCL to accelerate model processing through distributed GPU support across clusters.

    C++distributed-systemsgbdtgbm
    Auf GitHub ansehen↗28,471
  • nvidia/nvidia-dockerAvatar von NVIDIA

    NVIDIA/nvidia-docker

    17,496Auf GitHub ansehen↗

    NVIDIA Docker is a container runtime wrapper that enables the use of host-level graphics processing units within isolated container environments. It functions as a containerized GPU orchestrator, mapping physical hardware resources into virtualized environments to support high-performance computing and machine learning workloads. The project provides a toolkit that facilitates integration between containerized applications and host-level graphics hardware. By utilizing a pre-start hook to intercept container creation, the runtime injects necessary device drivers and libraries into the isolate

    Provides libraries and utilities that enable seamless integration between containerized applications and host-level graphics hardware.

    cudadockergpu
    Auf GitHub ansehen↗17,496
  • gpujs/gpu.jsAvatar von gpujs

    gpujs/gpu.js

    15,377Auf GitHub ansehen↗

    This library is a JavaScript framework for general-purpose computing on graphics processing units. It enables the execution of parallel mathematical operations directly within the browser by offloading data-heavy calculations to graphics hardware. The project functions as a web-based math accelerator that converts standard JavaScript functions into shader code for execution on the graphics processor. It provides a unified interface that detects available graphics APIs and manages data transfer between system and graphics memory. To ensure compatibility across diverse environments, the library

    Accelerates computationally intensive tasks by executing parallel mathematical operations directly on the graphics processor using WebGL.

    JavaScriptglslgpgpugpu
    Auf GitHub ansehen↗15,377
  • dask/daskAvatar von dask

    dask/dask

    13,746Auf GitHub ansehen↗

    Dask ist ein Framework für paralleles Rechnen und ein verteilter Task-Scheduler, der darauf ausgelegt ist, Python-Data-Science-Workflows von einzelnen Maschinen auf große Cluster zu skalieren. Es fungiert als Cluster-Ressourcenmanager, der die Berechnungslogik orchestriert, indem Aufgaben und deren Abhängigkeiten als gerichtete azyklische Graphen dargestellt werden. Diese Architektur ermöglicht es dem System, die Verteilung von Workloads auf verfügbare Hardware zu automatisieren und gleichzeitig komplexe Ausführungsanforderungen zu verwalten. Das Projekt zeichnet sich durch eine Lazy-Evaluation-Engine aus, die Datenoperationen verzögert, bis sie explizit angefordert werden, was eine globale Graphoptimierung und effiziente Ressourcenzuweisung ermöglicht. Es integriert speicherbewusstes Data-Spilling, um Systemabstürze bei der Verarbeitung von Datensätzen zu verhindern, die den verfügbaren Speicher überschreiten, und nutzt Task-Graph-Fusion, um Sequenzen von Operationen in einzelne Ausführungsschritte zu kombinieren, wodurch Scheduling-Overhead und Inter-Node-Kommunikation minimiert werden. Die Plattform bietet eine umfassende Oberfläche für die Datenanalyse im großen Maßstab, einschließlich Unterstützung für verteiltes maschinelles Lernen, Integration in das Hochleistungsrechnen und parallele Datenverarbeitung. Sie bietet umfangreiche Werkzeuge für das Cluster-Lebenszyklusmanagement, Performance-Profiling und die Echtzeitüberwachung der Aufgabenausführung. Benutzer können diese Umgebungen über verschiedene Infrastrukturen hinweg bereitstellen, einschließlich lokaler Hardware, Cloud-Anbietern, containerisierten Systemen und Hochleistungsrechner-Clustern.

    Integrates GPU-accelerated estimators into distributed workflows to perform hyperparameter optimization across multiple nodes.

    Pythondasknumpypandas
    Auf GitHub ansehen↗13,746
  • cpp-taskflow/cpp-taskflowAvatar von cpp-taskflow

    cpp-taskflow/cpp-taskflow

    12,014Auf GitHub ansehen↗

    Cpp-taskflow is a C++ task-parallelism framework and task graph scheduler designed to manage and execute complex dependency graphs of parallel tasks across CPU and GPU hardware. It provides a parallel algorithm library for high-performance implementations of reductions, sorts, pipelines, and iterations. The framework distinguishes itself through its ability to offload heavy computational workloads from a task graph to graphics processors for acceleration. It also includes a task profiling tool and a performance analysis interface for visualizing task execution flow and dependency structures t

    Provides libraries for offloading intensive scientific computations from the C++ execution graph to the GPU.

    C++
    Auf GitHub ansehen↗12,014
  • cupy/cupyAvatar von cupy

    cupy/cupy

    11,000Auf GitHub ansehen↗

    CuPy ist eine CUDA-Array-Computing-Bibliothek, die eine NumPy-kompatible Schnittstelle für die Ausführung von Array-Operationen und numerischen Berechnungen auf NVIDIA GPUs implementiert. Sie dient als GPU-beschleunigte numerische Bibliothek und CUDA-basierte SciPy-Implementierung, die rechenintensive Aufgaben auf Grafikhardware auslagert, um die Verarbeitungsgeschwindigkeit für wissenschaftliche und technische Workloads zu erhöhen. Die Bibliothek ermöglicht den Austausch von Tensoren zwischen verschiedenen Frameworks, wodurch Datenpuffer zwischen verschiedenen Deep-Learning-Frameworks unter Verwendung standardisierter Speicherlayouts geteilt werden können, um Speicherkopien zu vermeiden. Sie unterstützt zudem die Integration benutzerdefinierter GPU-Kernel, wodurch Array-Daten mit Low-Level-APIs verbunden werden können, um eine präzise Kontrolle über die Hardwareausführung zu ermöglichen. Das Projekt deckt im Wesentlichen Workflows für Array-Verarbeitung und wissenschaftliches Rechnen mit hoher Leistung ab. Zu den Fähigkeiten gehören die Beschleunigung von Array-Berechnungen und die Bereitstellung von Werkzeugen für numerische Berechnungen im großen Maßstab.

    Serves as a GPU acceleration library for offloading heavy numerical array calculations to graphics hardware.

    Python
    Auf GitHub ansehen↗11,000
  • wasabeef/glide-transformationsAvatar von wasabeef

    wasabeef/glide-transformations

    9,888Auf GitHub ansehen↗

    This is a Glide image transformation library for Android that provides a collection of image processing filters and shapes. It functions as a suite of hardware-accelerated tools for image cropping, artistic filtering, and transformation pipeline management. The project distinguishes itself through an image filter pipeline that allows for sequential transformation chaining, enabling multiple visual effects and color modifications to be applied in a single pass. It utilizes GPU acceleration to implement artistic effects such as pixelation, sketching, and blur. The library covers a broad range

    Provides hardware-accelerated artistic filters such as toon, sepia, sketch, and pixelation.

    Javaandroidandroid-libraryglide
    Auf GitHub ansehen↗9,888
  • dusty-nv/jetson-inferenceAvatar von dusty-nv

    dusty-nv/jetson-inference

    8,734Auf GitHub ansehen↗

    jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

    Configures container runtimes to enable hardware-accelerated applications to run inside portable containers.

    C++caffecomputer-visiondeep-learning
    Auf GitHub ansehen↗8,734
  • pixieditor/pixieditorAvatar von PixiEditor

    PixiEditor/PixiEditor

    7,840Auf GitHub ansehen↗

    PixiEditor is a multi-functional graphics suite that serves as a pixel art editor, a node-based graphics editor, and a vector graphics tool. It functions as a shader-based painting tool and 2D animation software, providing a comprehensive environment for creating raster images and frame-by-frame motion. The project is distinguished by its use of node-based workflows for building complex image transformations, visual effects, and custom digital brush designs. It utilizes a shader-based brush engine and a node graph to define personalized painting tool behaviors and procedural animations. The

    Utilizes GPU acceleration to perform complex image modifications by sampling colors and applying logic.

    C#2davaloniauicsharp
    Auf GitHub ansehen↗7,840
  • hybridgroup/gocvAvatar von hybridgroup

    hybridgroup/gocv

    7,463Auf GitHub ansehen↗

    GoCV is a computer vision library and Go language binding for OpenCV. It serves as an image processing toolkit and deep learning inference engine, providing programmatic access to a wide range of algorithms for image manipulation, object detection, and video analysis. The project differentiates itself through high-performance native bindings and hardware acceleration. It utilizes a foreign function interface to map Go calls to C++ functions and includes a hardware-agnostic backend dispatch to route neural network tasks to computation engines such as CUDA and OpenVINO. The library covers a br

    Executes arithmetic functions and morphology filters on the GPU to increase processing speed.

    Go
    Auf GitHub ansehen↗7,463
  • feast-dev/feastAvatar von feast-dev

    feast-dev/feast

    6,727Auf GitHub ansehen↗

    Feast is an open-source feature store for machine learning that provides a central platform for defining, storing, and serving features across both training and inference workflows. It operates as a declarative system where feature definitions are written as code in Python files, synchronized to a central registry, and made available for low-latency online retrieval or point-in-time correct historical joins for training datasets. The project abstracts storage behind a pluggable architecture, allowing offline and online backends to be swapped without changing retrieval logic, and coordinates ma

    Feast assigns GPU nodes to transformation workers through configuration, enabling GPU-native libraries for batch processing.

    Pythonbig-datadata-engineeringdata-quality
    Auf GitHub ansehen↗6,727
  • rocm/rocmAvatar von ROCm

    ROCm/ROCm

    6,645Auf GitHub ansehen↗

    Provides optimized libraries for mixed-precision matrix operations and HPC workloads on AMD GPUs.

    Shelldocumentation
    Auf GitHub ansehen↗6,645
  • nvidia/warpAvatar von NVIDIA

    NVIDIA/warp

    6,233Auf GitHub ansehen↗

    Warp is a Python framework that JIT-compiles Python functions into CUDA kernels for GPU-accelerated parallel computation, with built-in automatic differentiation and multi-framework array interoperability. At its core, it provides a GPU kernel compilation system that enables writing and executing custom GPU kernels directly from Python, while supporting automatic gradient computation through those kernels for integration with machine learning pipelines. The framework also includes tile-based cooperative computing, where thread blocks partition into tiles for shared-memory and tensor-core opera

    Switches on GPU-accelerated implementations for FFT, matrix multiply, and solver operations using cuFFTDx, cuBLASDx, and cuSolverDx.

    Pythoncudadifferentiable-programminggpu
    Auf GitHub ansehen↗6,233
  • nvidia/isaac-gr00tAvatar von NVIDIA

    NVIDIA/Isaac-GR00T

    6,222Auf GitHub ansehen↗

    Runs over 5,000 GPU-accelerated primitives for color conversion, filtering, thresholding, and image manipulation up to 30x faster than CPU-only implementations.

    Jupyter Notebook
    Auf GitHub ansehen↗6,222
  • nvidia/daliAvatar von NVIDIA

    NVIDIA/DALI

    5,713Auf GitHub ansehen↗

    NVIDIA DALI is a GPU-accelerated data loading and preprocessing library designed for deep learning workflows. It constructs high-performance data pipelines that offload decoding, augmentation, and normalization to the GPU, eliminating CPU bottlenecks in training and inference. The library reads data from multiple storage formats and streams it directly into GPU memory, with support for multi-GPU execution to scale throughput across large-scale workloads. DALI distinguishes itself by enabling data pipelines to be built once and executed across multiple deep learning frameworks without code cha

    Builds and executes data processing pipelines on the GPU for deep learning training and inference.

    C++audio-processingdata-augmentationdata-processing
    Auf GitHub ansehen↗5,713
  • google-ai-edge/litert-lmAvatar von google-ai-edge

    google-ai-edge/LiteRT-LM

    5,619Auf GitHub ansehen↗

    LiteRT-LM ist ein Hochleistungs-Inferenz-Framework, das darauf ausgelegt ist, Large Language Models lokal auf Mobil-, Desktop- und IoT-Hardware auszuführen. Es dient als On-Device-Modell-Laufzeitumgebung, die CPU-, GPU- und NPU-Beschleunigung nutzt, um eine Verarbeitung mit geringer Latenz zu ermöglichen. Das Framework zeichnet sich durch die Fähigkeit aus, Text-, Bild- und Audioeingaben über eine einzige multimodale Inferenz-Engine zu verarbeiten. Es verfügt über einen lokalen HTTP-Server, der OpenAI-kompatible API-Endpunkte emuliert, sowie eine WebGPU-basierte Laufzeitumgebung zur Ausführung von Modellen direkt im Webbrowser. Um die Zuverlässigkeit der Ausgabe zu gewährleisten, enthält es einen eingeschränkten Textgenerator, der JSON-Schemas oder Grammatikregeln für Modellantworten erzwingt. Das Projekt bietet umfassende Funktionen für zustandsbehaftetes Konversationsmanagement, spekulative Dekodierung für höhere Token-Generierungsgeschwindigkeiten und eine Tool-Calling-Schnittstelle, die Modellanfragen auf externe Funktionen abbildet. Es beinhaltet zudem eine spezialisierte Integration für das Apple-Ökosystem und ein dediziertes Plugin für die Modellausführung in Flutter. Benutzer können Modelle über eine Befehlszeilenschnittstelle ausführen oder sie über native APIs in Anwendungen integrieren.

    Reduces inference latency on mobile GPUs by employing multi-token prediction strategies.

    C++
    Auf GitHub ansehen↗5,619
  • fla-org/flash-linear-attentionAvatar von fla-org

    fla-org/flash-linear-attention

    5,248Auf GitHub ansehen↗

    Flash Linear Attention is a training framework and inference engine for sequence models that use linear attention and state space mechanisms, designed to process long contexts with reduced memory and compute overhead. It provides hardware-optimized token mixing layers and fused CUDA kernels that minimize memory bandwidth and launch overhead across different GPU architectures, and includes a causal inference engine that generates text token-by-token using cached hidden states for efficient autoregressive decoding. The project supports building hybrid sequence models that interleave standard at

    Provides hardware-optimized token mixing layers and fused CUDA kernels that minimize memory bandwidth and launch overhead across different GPU architectures.

    Pythonlarge-language-modelsmachine-learning-systemsnatural-language-processing
    Auf GitHub ansehen↗5,248
  • tile-ai/tilelangAvatar von tile-ai

    tile-ai/tilelang

    5,226Auf GitHub ansehen↗

    TileLang is a Python-embedded domain-specific language compiler that JIT-compiles and autotunes GPU kernels. It uses a tile-based DSL, automatic software pipelining, and parallel autotuning to generate optimized GPU kernels at runtime. It supports tensor core operations with Pythonic syntax, automatic memory management, and thread mapping. The compiler searches over tile sizes, thread counts, and scheduling policies, compiling and benchmarking candidates in parallel to find the fastest kernel. It also caches compiled binaries and tuning results to disk for reuse across sessions. TileLang inc

    Provides accelerated implementations of common math functions on GPU and CPU.

    Python
    Auf GitHub ansehen↗5,226
  • stability-ai/stableswarmuiAvatar von Stability-AI

    Stability-AI/StableSwarmUI

    4,929Auf GitHub ansehen↗

    StableSwarmUI ist eine Weboberfläche und ein Backend-Orchestrator für die Stable Diffusion-Bildgenerierung. Es fungiert als verteilter GPU-Bildgenerator und modulare KI-Bild-Pipeline und bietet einen zentralen Controller zur Verwaltung von Bildgenerierungsanfragen. Das System zeichnet sich durch die Fähigkeit aus, Generierungsaufgaben auf mehrere Grafikprozessoren aufzuteilen, um den Batch-Durchsatz zu erhöhen. Es nutzt eine Backend-agnostische Schnittstelle, um eine Verbindung zu lokalen Servern, Remote-Servern und Cloud-APIs herzustellen, und enthält einen grafbasierten visuellen Workflow-Designer für die Definition komplexer Bildverarbeitungsoperationen. Die Plattform umfasst ein dynamisches Plugin-Erweiterungssystem für das Hinzufügen benutzerdefinierter Funktionen und automatisierte Dienstprogramme für die Bereitstellung systemweiter Abhängigkeiten. Sie kombiniert modulare Generierungstools und schnelle Bearbeitungsoberflächen mit der Fähigkeit, Arbeitslasten über verteilte Hardware hinweg weiterzuleiten.

    Orchestrates the distribution of large image generation batches across multiple available GPUs to increase throughput.

    C#aiimage-generationstable-diffusion
    Auf GitHub ansehen↗4,929
Vorherige12Nächste
  1. Home
  2. DevOps & Infrastructure
  3. GPU Acceleration Libraries

Unter-Tags erkunden

  • Distributed GPU Task Runners1 Sub-TagExecution of arbitrary functions on GPU-accelerated hardware across a cluster. **Distinct from GPU Acceleration Libraries:** Distinct from general GPU acceleration libraries: focuses on distributed task orchestration rather than local library calls.
  • Edge Numerical Library InstallersInstalling optimized numerical computing packages for accelerated math operations on ARM64 edge hardware. **Distinct from GPU Acceleration Libraries:** Distinct from GPU Acceleration Libraries: focuses on installing numerical libraries specifically for edge devices, not general GPU library setup.
  • GPU Accelerated Image Operators1 Sub-TagHardware-accelerated implementation of arithmetic and morphological image filters. **Distinct from GPU Acceleration Libraries:** Focuses on specific image processing operators (arithmetic/morphology) rather than general GPU library setup.
  • GPU Container Toolkits1 Sub-TagLibraries and utilities enabling integration between containerized applications and host-level graphics hardware. **Distinct from GPU Acceleration Libraries:** Distinct from GPU Acceleration Libraries: focuses on the integration toolkit for container-to-hardware communication.
  • JavaScript GPGPU LibrariesJavaScript libraries that provide interfaces for general-purpose computing on graphics hardware. **Distinct from GPU Acceleration Libraries:** Distinct from GPU Acceleration Libraries: focuses on the JavaScript ecosystem and browser-based GPGPU, not general system-level GPU libraries.
  • Math Library Accelerators3 Sub-TagsEnabling GPU-accelerated implementations of FFT, matrix multiply, and solver operations via dedicated math libraries. **Distinct from GPU Acceleration Libraries:** Distinct from general GPU Acceleration Libraries: focuses on enabling specific math library backends (cuFFTDx, cuBLASDx, cuSolverDx) rather than general GPU offloading.
  • OrchestrationIntegration of GPU-accelerated libraries into distributed workflows for large-scale model training and optimization. **Distinct from GPU Acceleration Libraries:** Distinct from GPU Acceleration Libraries: focuses on the orchestration of distributed GPU tasks rather than the libraries themselves.
  • Token Mixing AcceleratorsGPU kernels and libraries that accelerate token mixing operations in sequence models, reducing memory bandwidth and compute overhead. **Distinct from GPU Acceleration Libraries:** Distinct from general GPU Acceleration Libraries: focuses specifically on token mixing operations for sequence models rather than broad GPU compute acceleration.
  • Zero-Copy Buffer InteroperabilityMechanisms for sharing GPU memory buffers between different libraries without duplicating data to system memory. **Distinct from GPU Acceleration Libraries:** Focuses on the high-performance sharing of memory buffers between libraries, rather than general GPU offloading or library integration.