Search Results for "gpu processing" - Page 6
Sort By:
Showing 212 open source projects for "gpu processing"
View related business solutions-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
1
TensorFlowOnSpark
TensorFlowOnSpark brings TensorFlow programs to Apache Spark clusters
By combining salient features from the TensorFlow deep learning framework with Apache Spark and Apache Hadoop, TensorFlowOnSpark enables distributed deep learning on a cluster of GPU and CPU servers. It enables both distributed TensorFlow training and inferencing on Spark clusters, with a goal to minimize the amount of code changes required to run existing TensorFlow programs on a shared grid. -
2
Flux3D.jl
3D computer vision library in Julia
Flux3D.jl is a 3D vision library, written completely in Julia. This package utilizes Flux.jl and Zygote.jl as its building blocks for training 3D vision models and for supporting differentiation. This package also have support of CUDA GPU acceleration with CUDA.jl. -
3
glfx.js
An image effects library for JavaScript using WebGL
glfx.js is a JavaScript image-effects library that uses WebGL to apply real-time filters and transformations directly in the browser. It exposes a simple API where images are uploaded into GPU textures, processed with shader-based filters, and rendered to a WebGL canvas. Because the work is done on the GPU, many effects that would be too slow in pure JavaScript (like complex blurs, lens effects, or tilt-shift) can run interactively, even on large images. The library is structured around... -
4
SVoice (Speech Voice Separation)
We provide a PyTorch implementation of the paper Voice Separation
SVoice is a PyTorch-based implementation of Facebook Research’s study on speaker voice separation as described in the paper “Voice Separation with an Unknown Number of Multiple Speakers.” This project presents a deep learning framework capable of separating mixed audio sequences where several people speak simultaneously, without prior knowledge of how many speakers are present. The model employs gated neural networks with recurrent processing blocks that disentangle voices over multiple... -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
5
KoGPT
KakaoBrain KoGPT (Korean Generative Pre-trained Transformer)
KoGPT is a Korean language model based on OpenAI’s GPT architecture, designed for various natural language processing (NLP) tasks such as text generation, summarization, and dialogue systems. -
6
Vivid 3D
Vivid is a modern C++ 3D engine using OpenGL4+
Vivid is a modern C++ 3D engine using OpenGL4+. It is written using Visual C++ 2022, and relies on several open source projects to achieve it's goal of making it easy and run to make modern games with it. -
7
jetson-ffmpeg
ffmpeg support on jetson nano
...It provides a bridge between FFmpeg and NVIDIA’s proprietary APIs, allowing developers to leverage on-device hardware encoders and decoders for improved performance. The project includes a library and patch system that modifies FFmpeg builds to enable NVMPI-based acceleration. This allows efficient processing of video streams on embedded systems without overloading CPU resources. jetson-ffmpeg is particularly useful for edge computing applications such as robotics, surveillance, and real-time streaming. It requires building both the library and a patched version of FFmpeg to fully enable hardware features. Overall, it extends FFmpeg functionality to better suit embedded GPU-powered environments. -
8
TurboTransformers
Fast and user-friendly runtime for transformer inference
TurboTransformers is a high-performance inference framework optimized for running Transformer models efficiently on CPUs and GPUs. It improves latency and throughput for NLP applications. -
9
ArrayFire.jl
Julia wrapper for the ArrayFire library
ArrayFire is a library for GPU and accelerated computing. ArrayFire.jl wraps the ArrayFire library for Julia, and provides a Julia interface. Install ArrayFire library: either download a binary from the official site, or you can build from source. -
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
10
Tdarr V2
Distributed transcode automation using FFmpeg/HandBrake
Tdarr is a distributed media transcoding and automation system designed to manage and optimize large audio and video libraries across multiple machines. It operates through a central server and multiple worker nodes that process files in parallel, leveraging both CPU and GPU resources for efficient transcoding. The system uses FFmpeg and HandBrake to convert media files according to user-defined rules, such as codec standardization, bitrate optimization, or format compatibility. Tdarr also includes advanced features like health checks, plugin-based processing pipelines, and automated scheduling to maintain libraries continuously. ... -
11
PyText
A natural language modeling framework based on PyTorch
PyText is a deep-learning based NLP modeling framework built on PyTorch. PyText addresses the often-conflicting requirements of enabling rapid experimentation and of serving models at scale. It achieves this by providing simple and extensible interfaces and abstractions for model components, and by using PyTorch’s capabilities of exporting models for inference via the optimized Caffe2 execution engine. We use PyText at Facebook to iterate quickly on new modeling ideas and then seamlessly... -
12
opencv4nodejs
Nodejs bindings to OpenCV 3 and OpenCV 4
OpenCV4NodeJS is a Node.js binding for OpenCV, allowing developers to integrate computer vision capabilities directly into JavaScript applications for image processing, object detection, and facial recognition. -
13
The intellectual system of Eidos
http://lc.kubagro.ru/
http://lc.kubagro.ru/ http://lc.kubagro.ru/aidos/index.htm http://lc.kubagro.ru/aidos/_Aidos-X.htm On the IBM PC, the Eidos system started working in 1992. MS Windows has been running since 2012. Implemented in Alaska+Express. I want to try to translate some modes, and maybe all of them, to the Harbor. The full source text in a single file is here: http://lc.kubagro.ru/__AIDOS-X.txt Responsible Secretary Kubgau scientific journal, Professor of computer science Department Kubgau... -
14
FastoCloud PRO
IPTV/NVR/CCTV/Video cloud https://fastocloud.com
IPTV/Video cloud Features: Cross-platform (Linux, MacOSX, FreeBSD, Raspbian/Armbian) GPU/CPU Encode/Decode/Post Processing Stream statistics CCTV Adaptive hls streams Load balancing Temporary urls HLS push EPG scanning Subtitles to text conversions AD insertion Logo overlay Video effects Relays Timeshifts Catchups Playlists Restream/Transcode from online streaming services like Youtube, Twitch Mozaic Many Outputs Physical Inputs Streaming Protocols File Formats Presets Vods/Series server-side support Pay per view channels Channels on demand HTTP Live Streaming (HLS) server-side support Public API, client server communication via JSON RPC Protocol gzip compression Deep learning video analysis Supported deep learning frameworks: Tensorflow NCSDK Caffe ML Hardware: -
15
cocoNLP
A Chinese information extraction tool
cocoNLP is a lightweight natural-language processing toolkit geared toward practical information extraction from raw text, especially for Chinese and mixed Chinese–English content. Instead of requiring a heavy pipeline, it focuses on quick wins such as extracting names, places, organizations, emails, phone numbers, and dates directly from unstructured sentences. The project blends pattern-based methods with NLP heuristics, giving developers dependable results for real-world texts like chats,... -
16
AwesomeBump
Open Source graphic tool and alternative to Insane Bump
...It was made as an alternative to known gimp plugin Insane Bump or the commercial tool Crazy Bump. It is designed to generate normal, height, specular or ambient occlusion, metallic, roughness and other textures from a single image. Most of the image processing is done on GPU so the program runs very fast and all the parameters can be changed in real time. -
17
Inviwo
Interactive Visualization Workshop
...Built in C++ with a modular, extensible architecture, Inviwo combines a visual editor (for creating data pipelines) with a powerful runtime engine that supports real-time rendering, interaction, and GPU-accelerated processing. It’s widely used in scientific domains for building and sharing visualizations of complex data such as medical imaging, simulations, and machine learning models. The platform supports both novice users through its graphical interface and advanced users through scripting and plugin development. -
18
GPUImage 2
Framework for GPU-accelerated video and image processing
GPUImage 2 is the second generation of the GPUImage framework, an open source project for performing GPU-accelerated image and video processing on Mac, iOS, and now Linux. The original GPUImage framework was written in Objective-C and targeted Mac and iOS, but this latest version is written entirely in Swift and can also target Linux and future platforms that support Swift code. The objective of the framework is to make it as easy as possible to set up and perform realtime video processing or machine vision against image or video sources. ... -
19
MultiPathNet
A Torch implementation of the object detection network
MultiPathNet is a Torch-7 implementation of the “A MultiPath Network for Object Detection” paper (BMVC 2016), developed by Facebook AI Research. It extends the Fast R-CNN framework by introducing multiple network “paths” to enhance feature extraction and object recognition robustness. The MultiPath architecture incorporates skip connections and multi-scale processing to capture both fine-grained details and high-level context within a single detection pipeline. This results in improved... -
20
GPU, a Global Processing Unit
A framework for distributed computing
An extensible framework for distributed computing on P2P grids. We support peaceful free and open research and build an internet supercomputer. We render movies, solve Eternity puzzles, predict climate and improve a ~30 GHz cluster of clients. -
21
Tensorpack
A Neural Net Training Interface on TensorFlow, with focus on speed
...On common CNNs, it runs training 1.2~5x faster than the equivalent Keras code. Your training can probably gets faster if written with Tensorpack. Scalable data-parallel multi-GPU / distributed training strategy is off-the-shelf to use. Squeeze the best data loading performance of Python with tensorpack.dataflow. Symbolic programming (e.g. tf.data) does not offer the data processing flexibility needed in research. Tensorpack squeezes the most performance out of pure Python with various auto parallelization strategies. ... -
22
LUMINOTH
Deep Learning toolkit for Computer Vision
LUMINOTH is an open-source deep learning toolkit designed for computer vision tasks, particularly object detection. The framework is implemented in Python and built on top of TensorFlow and the Sonnet neural network library, providing a modular environment for training and deploying detection models. It was created to simplify the process of building and experimenting with deep learning models capable of identifying objects within images. Luminoth includes support for popular object... -
23
Bender
Easily craft fast Neural Networks on iOS
...With Core ML, you can integrate trained machine learning models into your app, it supports Caffe and Keras 1.2.2+ at the moment. Apple released conversion tools to create CoreML models which then can be run easily. Finally, there is no easy way to add additional pre or post-processing layers to run on the GPU. -
24
PixelFlow
A Processing/Java library for high performance GPU-Computing (GLSL)
PixelFlow is a Processing library focused on advanced graphics and visual effects, offering an extensive suite of GPU-based tools for visual artists, researchers, and creative coders. It enables real-time simulation and rendering of complex effects such as fluid dynamics, reaction-diffusion systems, soft shadows, and more, all powered by GLSL shaders. Its modular structure allows for chaining and composing various visual effects easily, making it ideal for installations, performances, and visual experimentation. -
25
Starling Filters
A collection of filters for use with the Starling AS3 framework
Starling-Filters is an open-source collection of filter effects for the Starling AS3 framework. These filters allow developers using Starling (a GPU accelerated 2D rendering framework in Flash/AIR) to apply image processing / visual effects (e.g. blur, glow, etc.) in their Starling-based applications. The repo has versions for Starling 2.0 (on master) and older filters archived for Starling 1.x. A collection of filters for use with the Starling AS3 framework. The master branch contains filters for use with Starling 2.0.
