Showing 86 open source projects for "gpu processing"

View related business solutions
  • Our Free Plans just got better! | Auth0 Icon
    Our Free Plans just got better! | Auth0

    With up to 25k MAUs and unlimited Okta connections, our Free Plan lets you focus on what you do best—building great apps.

    You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
    Try free now
  • Earn up to 16% annual interest with Nexo. Icon
    Earn up to 16% annual interest with Nexo.

    Access competitive interest rates on your digital assets.

    Generate interest, borrow against your crypto, and trade a range of cryptocurrencies — all in one platform. Geographic restrictions, eligibility, and terms apply.
    Get started with Nexo.
  • 1
    Jasna

    Jasna

    Video restoration tool

    ...A graphical interface provides processing queues, presets, previews, and a segment editor for selecting specific regions. Users can also watch restored videos in real time without exporting new files. Jasna supports VR180 content, batch processing, and command-line automation. It runs on Windows and Linux with compatible NVIDIA GPUs and experimental AMD acceleration. Additional sharpening and enhancement models are available through supporter licensing.
    Downloads: 2,245 This Week
    Last Update:
    See Project
  • 2
    nunif

    nunif

    Misc; latest version of waifu2x; 2D video to stereo 3D video

    nunif is a deep learning–based image processing framework focused on image upscaling, restoration, denoising, and enhancement tasks using neural network models. The project provides a collection of AI-powered utilities designed primarily for anime-style artwork, illustrations, and high-quality image restoration workflows. It includes command-line tools and graphical interfaces for applying trained neural models to improve image resolution and visual clarity while minimizing artifacts. nunif supports GPU acceleration and batch processing, making it suitable for creators, archivists, and enthusiasts handling large image collections. ...
    Downloads: 11 This Week
    Last Update:
    See Project
  • 3
    rembg

    rembg

    Rembg is a tool to remove images background

    Rembg is a powerful tool that utilizes AI (specifically U^2-Net) to automatically remove backgrounds from images, offering a streamlined command-line interface and Docker support. It's ideal for batch processing and integrates smoothly into workflows
    Downloads: 34 This Week
    Last Update:
    See Project
  • 4
    VideOCR

    VideOCR

    Extract hardcoded subtitles from videos via a simple GUI

    ...Users can navigate video timelines and select a specific extraction area using a cropping rectangle. The application supports more than 200 languages through its OCR capabilities. Local processing uses PaddleOCR, while an optional Google Lens mode provides cloud-assisted recognition. Advanced settings control extraction behavior, including frame sampling and processing parameters. GPU acceleration can improve performance on compatible hardware. A command-line version supports automated processing and Docker deployment. VideOCR runs on Windows and Linux.
    Downloads: 15 This Week
    Last Update:
    See Project
  • Already Paying for an RMM? Get 50% Off Splashtop AEM Icon
    Already Paying for an RMM? Get 50% Off Splashtop AEM

    Switch to Splashtop AEM and save up to 50% in your first year

    Automated OS and third-party patching for Windows and macOS, CVE prioritization with AI patch summaries, and built-in remote control that also supports Linux. Qualifying organizations switching from another RMM get up to 50% off year one.
    Get Started
  • 5
    Whisper Local

    Whisper Local

    Free, open-source, 100% offline AI dictation for Windows & macOS

    ...It offers smart punctuation, transcription cleanup, personalized vocabulary corrections, and configurable writing styles. Optional Ollama integration provides local AI-powered text rewriting and refinement. NVIDIA and AMD GPU acceleration can improve transcription performance, while CPU processing remains available. Additional tools include searchable transcription history, application-specific profiles, and a local OpenAI-compatible transcription API. All speech processing remains on the user's device.
    Downloads: 25 This Week
    Last Update:
    See Project
  • 6
    ODM

    ODM

    A command line toolkit to generate maps, point clouds, 3D models

    ...It can process photographs captured by drones, balloons, kites, and other aerial platforms. Outputs include classified point clouds, textured 3D models, georeferenced orthophotos, and digital elevation models. The processing pipeline integrates specialized open-source projects for reconstruction, meshing, geospatial conversion, and point-cloud processing. ODM runs on Windows, macOS, and Linux and is commonly deployed through Docker. GPU acceleration is available for selected feature-extraction workloads. NodeODM can expose the processing engine over a network for integration with other applications.
    Downloads: 5 This Week
    Last Update:
    See Project
  • 7
    VoiceStudio

    VoiceStudio

    VoiceStudio is the open-source, fully-local ElevenLabs alternative

    VoiceStudio is an open-source, local-first platform for speech generation, voice cloning, transcription, dubbing, and audio production. It can clone voices from short reference recordings or design new voices from characteristics such as accent, pitch, age, and delivery style. Video dubbing combines transcription, translation, speaker preservation, speech synthesis, and final video export. It also supports multi-voice stories, audiobooks, dictation, vocal isolation, and speaker diarization....
    Downloads: 471 This Week
    Last Update:
    See Project
  • 8
    HunyuanVideo

    HunyuanVideo

    HunyuanVideo: A Systematic Framework For Large Video Generation Model

    HunyuanVideo is a cutting-edge framework designed for large-scale video generation, leveraging advanced AI techniques to synthesize videos from various inputs. It is implemented in PyTorch, providing pre-trained model weights and inference code for efficient deployment. The framework aims to push the boundaries of video generation quality, incorporating multiple innovative approaches to improve the realism and coherence of the generated content. Release of FP8 model weights to reduce GPU...
    5.0 out of 5 stars 1 Review
    Downloads: 20 This Week
    Last Update:
    See Project
  • 9
    GPU Puzzles

    GPU Puzzles

    Solve puzzles. Learn CUDA

    ...By solving progressively more complex puzzles, learners gain a practical understanding of how parallel algorithms operate on graphics processing units. The project emphasizes experimentation and problem solving, encouraging learners to discover GPU programming techniques through trial and exploration. It can be run in cloud environments such as Google Colab, making it easy for beginners to start experimenting without configuring local GPU hardware.
    Downloads: 1 This Week
    Last Update:
    See Project
  • $300 Free Credits to Build on Google Cloud Icon
    $300 Free Credits to Build on Google Cloud

    New customers can spin up VMs, build with AI, and query data at no cost.

    Put your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
    Start Free
  • 10
    Kornia

    Kornia

    Open Source Differentiable Computer Vision Library

    Kornia is a differentiable computer vision library for PyTorch. It consists of a set of routines and differentiable modules to solve generic computer vision problems. At its core, the package uses PyTorch as its main backend both for efficiency and to take advantage of the reverse-mode auto-differentiation to define and compute the gradient of complex functions. Inspired by existing packages, this library is composed by a subset of packages containing operators that can be inserted within...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 11
    ProtoMotions

    ProtoMotions

    ProtoMotions is a GPU-accelerated simulation and learning framework

    ...Policies can be tested across Isaac Gym, Isaac Lab, Newton, Genesis, MuJoCo, and high-fidelity Isaac Sim environments. Its deployment pipeline exports ONNX policies with observation processing included, simplifying transfers from simulation to real Unitree G1 hardware. The framework also supports procedural scene generation and motion authoring from Kimodo text-to-motion outputs.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 12
    Pyreft

    Pyreft

    ReFT: Representation Finetuning for Language Models

    PyreFT is a tool by Stanford NLP for fine-tuning transformer models with an emphasis on efficient, resource-conserving training and customizability for NLP tasks.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 13
    napari

    napari

    A fast, interactive, multi-dimensional image viewer for python

    napari is a Python-based multidimensional image viewer designed for exploring, annotating, and analyzing large scientific datasets. It provides interactive visualization of 2D, 3D, and higher-dimensional images through a Qt interface powered by GPU-accelerated rendering with vispy. Users can combine images, segmentation labels, points, vectors, shapes, and surfaces in adjustable visualization layers. The viewer supports browsing image stacks, examining spatial relationships, and creating annotations directly on datasets. Integration with NumPy, SciPy, and Jupyter notebooks enables programmatic image processing and analysis. ...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 14
    KServe

    KServe

    Standardized Serverless ML Inference Platform on Kubernetes

    ...It aims to solve production model serving use cases by providing performant, high abstraction interfaces for common ML frameworks like Tensorflow, XGBoost, ScikitLearn, PyTorch, and ONNX. It encapsulates the complexity of autoscaling, networking, health checking, and server configuration to bring cutting edge serving features like GPU Autoscaling, Scale to Zero, and Canary Rollouts to your ML deployments. It enables a simple, pluggable, and complete story for Production ML Serving including prediction, pre-processing, post-processing and explainability. KServe is being used across various organizations.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 15
    Colossal-AI

    Colossal-AI

    Making large AI models cheaper, faster and more accessible

    The Transformer architecture has improved the performance of deep learning models in domains such as Computer Vision and Natural Language Processing. Together with better performance come larger model sizes. This imposes challenges to the memory wall of the current accelerator hardware such as GPU. It is never ideal to train large models such as Vision Transformer, BERT, and GPT on a single GPU or a single machine. There is an urgent demand to train models in a distributed environment. ...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 16
    NVIDIA NeMo

    NVIDIA NeMo

    Toolkit for conversational AI

    ...NeMo uses PyTorch Lightning for easy and performant multi-GPU/multi-node mixed-precision training. Supported models: Jasper, QuartzNet, CitriNet, Conformer-CTC, Conformer-Transducer, Squeezeformer-CTC, Squeezeformer-Transducer, ContextNet, LSTM-Transducer (RNNT), LSTM-CTC. NGC collection of pre-trained speech processing models.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 17
    NeuralScreen

    NeuralScreen

    DLSS 5 NR on your whole Windows desktop, in real time with Boost

    NeuralScreen applies NVIDIA DLSS neural rendering to the Windows desktop through a real-time graphical overlay. It processes games, videos, photographs, and other on-screen content without requiring individual application integration. Users can enhance the entire display or select a particular window for processing. Customizable rendering profiles adjust enhancement strength, color, and camera effects. Boost Mode reduces processing resolution to improve performance while preserving the final...
    Downloads: 45 This Week
    Last Update:
    See Project
  • 18
    CUDA Python

    CUDA Python

    Performance meets Productivity

    ...It integrates tightly with the broader Python GPU ecosystem, including Numba for kernel compilation and CCCL for parallel primitives, allowing developers to write performant code without leaving Python. The toolkit also includes utilities for profiling, memory management, distributed computing, and numerical operations, making it suitable for scientific computing, AI, and data processing workloads.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 19
    stt

    stt

    Voice Recognition to Text Tool

    ...The project is designed to be easy to deploy: you can run a local Python server that exposes an HTTP API for uploading audio/video files and retrieving transcriptions in different formats. It supports GPU acceleration if available, enabling faster processing on compatible hardware but still offers reliable performance on CPUs alone.
    Downloads: 7 This Week
    Last Update:
    See Project
  • 20
    FlexLLMGen

    FlexLLMGen

    Running large language models on a single GPU

    FlexLLMGen is an open-source inference engine designed to run large language models efficiently on limited hardware resources such as a single GPU. The system focuses on high-throughput generation workloads where large batches of text must be processed quickly, such as large-scale data extraction or document analysis tasks. Instead of requiring expensive multi-GPU systems, the framework uses techniques such as memory offloading, compression, and optimized batching to run large models on...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 21
    clip-retrieval

    clip-retrieval

    Easily compute clip embeddings and build a clip retrieval system

    ...It allows developers to compute embeddings for both images and text efficiently and then index them for fast similarity search across massive datasets. The system is optimized for performance and scalability, capable of processing tens or even hundreds of millions of embeddings using GPU acceleration. It includes components for inference, indexing, filtering, and serving results through APIs, making it a complete pipeline for building production-ready retrieval systems. The framework also supports querying by image, text, or embedding, enabling flexible use cases such as reverse image search or multimodal content discovery. ...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 22
    Faster Whisper

    Faster Whisper

    Faster Whisper transcription with CTranslate2

    Faster Whisper is an optimized implementation of the Whisper speech recognition model designed to deliver significantly faster inference while maintaining comparable accuracy. It leverages efficient inference engines and optimized computation strategies to reduce latency and resource consumption. The system is particularly useful for real-time or large-scale transcription tasks where performance is critical. It supports multiple model sizes, allowing users to balance speed and accuracy based...
    Downloads: 171 This Week
    Last Update:
    See Project
  • 23
    Text Generation Inference

    Text Generation Inference

    Large Language Model Text Generation Inference

    Text Generation Inference is a high-performance inference server for text generation models, optimized for Hugging Face's Transformers. It is designed to serve large language models efficiently with optimizations for performance and scalability.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 24
    Practical-RIFE

    Practical-RIFE

    More practical frame interpolation approach

    ...Users can increase frame rates by two or four times through Python inference scripts. Configurable scaling options help process high-resolution footage while managing GPU memory requirements. Additional scripts support image sequence processing, comparison previews, and experimental video enhancement using SAFA. Lightweight model variants reduce computational demands. It is primarily intended for developers and engineers integrating frame interpolation into video processing workflows.
    Downloads: 2 This Week
    Last Update:
    See Project
  • 25
    FlashKDA

    FlashKDA

    High-performance Kimi Delta Attention kernels

    FlashKDA is an open-source library of high-performance CUDA kernels for Kimi Delta Attention, implemented on NVIDIA CUTLASS. It is intended to accelerate the forward pass used by KDA-based language models on modern NVIDIA GPUs. The package integrates with flash-linear-attention and can be selected automatically as the backend for chunk_kda during inference. It supports recurrent state input and output, variable-length batches, internal gating, query-key normalization, and beta activation....
    Downloads: 1 This Week
    Last Update:
    See Project
  • Previous
  • You're on page 1
  • 2
  • 3
  • 4
  • Next