Search Results for "cuda" - Page 2
Sort By:
Showing 309 open source projects for "cuda"
View related business solutions-
Our Free Plans just got better! | Auth0You 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.
-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
1
Triton
Development repository for the Triton language and compiler
Triton is a programming language and compiler framework specifically designed for writing highly efficient custom deep learning operations, particularly for GPUs. It aims to bridge the gap between low-level GPU programming, such as CUDA, and higher-level abstractions by providing a more productive and flexible environment for developers. Triton enables users to write optimized kernels for machine learning workloads while maintaining readability and control over performance-critical aspects like memory access patterns and parallel execution. The project leverages LLVM and MLIR to compile code into efficient GPU instructions, supporting both NVIDIA and AMD hardware. ... -
2
Model Zoo
Please do not feed the models
...The examples serve both as educational tools for learning Flux and as practical starting points for building new models. GPU acceleration is supported for most models through CUDA integration, enabling efficient training on compatible hardware. With community contributions encouraged, the Model Zoo acts as a hub for sharing and exploring diverse machine learning applications in Julia. -
3
RWKV Runner
A RWKV management and startup tool, full automation, only 8MB
...So it's combining the best of RNN and transformer - great performance, fast inference, fast training, saves VRAM, "infinite" ctxlen, and free text embedding. Moreover it's 100% attention-free. Default configs has enabled custom CUDA kernel acceleration, which is much faster and consumes much less VRAM. If you encounter possible compatibility issues, go to the Configs page and turn off Use Custom CUDA kernel to Accelerate. -
4
VibeTensor
Our first fully AI generated deep learning system
VibeTensor is a groundbreaking open-source research system software stack for deep learning that was uniquely generated almost entirely by AI coding agents under guided human supervision, demonstrating a new frontier in AI-assisted software engineering. It implements a PyTorch-style eager tensor library with a modern C++20 core that supports both CPU and CUDA backends, giving it the ability to manage tensors, automatic differentiation (autograd), and complex computation flows similar to mainstream frameworks. What makes VibeTensor remarkable is that every major component, from core libraries and dispatch systems to CUDA runtime support, caching allocators, and language bindings, was created and validated by coding agents using automated builds and tests rather than manual line-by-line human coding. ... -
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
5
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 -
6
Lucebox
Fast LLM speculative inference server for consumer hardware
...The project includes a native C++ HTTP server with an OpenAI-compatible API, making it usable with tools that already speak the Chat Completions format. It supports CUDA and ROCm workflows, with Docker images for NVIDIA and AMD GPU setups. The repository also includes harnesses for testing compatibility with clients such as Claude Code, Codex, OpenCode, Hermes, Pi, OpenClaw, and Open WebUI. It is most useful for developers and AI enthusiasts who want to run optimized local models with lower latency, faster token generation, and hardware-aware inference behavior. -
7
Chatterbox TTS Server
Self-host the powerful Chatterbox TTS model
...It also includes OpenAI-compatible API behavior, which helps developers connect it to existing tools that already expect that style of endpoint. The server can run on NVIDIA CUDA, AMD ROCm, or CPU, giving it flexibility across different hardware setups. Its main value is packaging a powerful TTS workflow into a practical service that can be accessed through a browser or integrated into other software. -
8
Koila
Prevent PyTorch's `CUDA error: out of memory` in just 1 line of code
...The system acts as a thin wrapper around PyTorch tensors and operations, meaning that it integrates easily into existing PyTorch code without requiring major changes to model implementations. It is particularly useful in environments where GPU resources are limited or where models frequently encounter CUDA memory errors. -
9
opencvsharp
OpenCV wrapper for .NET
...The native binding (libOpenCvSharpExtern) is already built in the docker image and you don't need to worry about it. OpenCvSharp won't work on Unity and Xamarin platform. For Unity, please consider using OpenCV for Unity or some other solutions. OpenCvSharp does not support CUDA. If you want to use the CUDA features, you need to customize the native bindings yourself. Objects of classes, such as Mat and MatExpr, have unmanaged resources and need to be manually released by calling the Dispose() method. Worst of all, the +, -, *, and other operators create new objects each time, and these objects need to be disposed of, or there will be memory leaks. ... -
$300 Free Credits to Build on Google CloudStart your next project with $300 in free Google Cloud credit. Spin up VMs, run containers, query petabytes in BigQuery, or build agents with Gemini Enterprise Agent Platform. Once your credits are used, keep building with 20+ always-free tier products including Compute Engine, Cloud Storage, GKE, and Cloud Run functions. No commitment required—just sign up and start building.
-
10
TensorRT
C++ library for high performance inference on NVIDIA GPUs
...With TensorRT, you can optimize neural network models trained in all major frameworks, calibrate for lower precision with high accuracy, and deploy to hyperscale data centers, embedded, or automotive product platforms. TensorRT is built on CUDA®, NVIDIA’s parallel programming model, and enables you to optimize inference leveraging libraries, development tools, and technologies in CUDA-X™ for artificial intelligence, autonomous machines, high-performance computing, and graphics. With new NVIDIA Ampere Architecture GPUs, TensorRT also leverages sparse tensor cores providing an additional performance boost. -
11
Stable Diffusion Version 2
High-Resolution Image Synthesis with Latent Diffusion Models
...The project sits within a larger ecosystem of Stability AI repositories (including inference-only reference implementations like SD3.5 and web UI projects) and the README points users toward compatible components, recommended CUDA/PyTorch versions. -
12
Dream Textures
Stable Diffusion built-in to Blender
...Outpaint to increase the size of an image by extending it in any direction. Perform style transfer and create novel animations with Stable Diffusion as a post processing step. Dream Textures has been tested with CUDA and Apple Silicon GPUs. Over 4GB of VRAM is recommended. -
13
Taichi
Productive, portable, and performant GPU programming in Python
...It uses JIT compilation (via LLVM and its runtime TiRT) to offload compute-heavy code to CPUs, GPUs, mobile devices, and embedded systems. With built-in support for sparse data structures (SNode), automatic differentiation, AOT deployment, and compatibility with CUDA, Vulkan, Metal, and OpenGL ES, it empowers disciplines like simulation, graphics, AI, and robotics -
14
GraphNeuralNetworks.jl
Graph Neural Networks in Julia
GraphNeuralNetworks.jl is a graph neural network library written in Julia and based on the deep learning framework Flux.jl. -
15
OpenCV
Open Source Computer Vision Library
OpenCV (Open Source Computer Vision Library) is a comprehensive open-source library for computer vision, machine learning, and image processing. It enables developers to build real-time vision applications ranging from facial recognition to object tracking. OpenCV supports a wide range of programming languages including C++, Python, and Java, and is optimized for both CPU and GPU operations. -
16
Nano-vLLM
A lightweight vLLM implementation built from scratch
...The project recreates the core functionality of vLLM in a simplified architecture written in approximately a thousand lines of Python, making it easier for developers and researchers to understand how modern LLM inference systems work. Despite its compact design, nano-vllm incorporates advanced optimization techniques such as prefix caching, tensor parallelism, and CUDA graph execution to achieve high performance during model inference. The engine is intended primarily for educational use, experimentation, and lightweight deployments where a full production-grade inference stack may be unnecessary. Its API closely mirrors that of the original vLLM framework, allowing developers familiar with vLLM to adopt the tool with minimal changes. -
17
Yao
Extensible, Efficient Quantum Algorithm Design for Humans
...Yao supports both forward-mode (faithful gradient) and reverse-mode automatic differentiation with its builtin engine optimized specifically for quantum circuits. Top performance for quantum circuit simulations. Its CUDA backend and batched quantum register support can make typical quantum circuits even faster. Yao is designed to be extensible. Its hierarchical architecture allows you to extend the framework to support and share your new algorithm and hardware. -
18
HOOMD-blue
Molecular dynamics and Monte Carlo soft matter simulation on GPUs
HOOMD-blue is a Python-driven particle simulation engine for molecular dynamics and hard-particle Monte Carlo simulations. It was designed from the ground up for GPU acceleration, with a high-performance C++ and CUDA backend. The software is especially useful for nano-scale, colloidal, polymer, soft matter, and materials simulations. Its Python interface lets users build simulation and analysis workflows using familiar scientific Python tools. HOOMD-blue supports efficient parallel execution and has been used for large-scale GPU-based simulations. ... -
19
Bonsai 27B
Run Bonsai (1-bit) and Ternary-Bonsai language models locally
...It supports the 1-bit Bonsai and higher-quality Ternary-Bonsai families in 1.7B, 4B, 8B, and 27B sizes. The models can run on macOS, Linux, and Windows through CPU, Metal, CUDA, Vulkan, ROCm, llama.cpp, or MLX backends. Its 27B models process text, images, screenshots, and PDFs while supporting reasoning and long-context conversations. They also provide OpenAI-compatible tool calling and optional MCP server integration for agentic workflows. Automated setup scripts install dependencies, download models, obtain binaries, and configure interactive interfaces. ... -
20
Nexa SDK
Nexa SDK is a comprehensive toolkit for supporting ONNX and GGML
...Additionally, it offers an OpenAI-compatible API server with JSON schema mode for function calling and streaming support, and a user-friendly Streamlit UI. Users can run Nexa SDK in any device with Python environment, and GPU acceleration is supported, including CUDA, Metal, and ROCm. An executable version is also available. -
21
SuiteSparse
The official SuiteSparse library: a suite of sparse matrix algorithms
The official SuiteSparse library: a suite of sparse matrix algorithms authored or co-authored by Tim Davis, Texas A&M University. -
22
NNlib.jl
Neural Network primitives with multiple backends
This package provides a library of functions useful for neural networks, such as softmax, sigmoid, batched multiplication, convolutions and pooling. Many of these are used by Flux.jl, which loads this package, but they may be used independently. -
23
PyTorch Geometric
Geometric deep learning extension library for PyTorch
...We have outsourced a lot of functionality of PyTorch Geometric to other packages, which needs to be additionally installed. These packages come with their own CPU and GPU kernel implementations based on C++/CUDA extensions. We do not recommend installation as root user on your system python. Please setup an Anaconda/Miniconda environment or create a Docker image. We provide pip wheels for all major OS/PyTorch/CUDA combinations. -
24
Cog
Package and deploy machine learning models using Docker containers
...Developers can define the runtime environment, dependencies, and Python versions required for their models, allowing Cog to build a consistent container environment that follows best practices. Cog also resolves compatibility issues between frameworks and GPU libraries by automatically selecting compatible combinations of CUDA, cuDNN, and machine learning frameworks such as PyTorch or TensorFlow. Cog automatically generates a RESTful HTTP API for running predictions, enabling models to be accessed programmatically through a built-in prediction server. -
25
qvac-fabric-llm.cpp
QVAC Fabric: cross-platform LLM inference and fine-tuning
...The project focuses on removing hardware limitations traditionally associated with LLM deployment by enabling support for a wide range of backends, including Vulkan, Metal, CUDA, and CPU, making it accessible on devices ranging from smartphones to enterprise servers. It introduces native LoRA fine-tuning capabilities that can be executed directly on consumer hardware, allowing developers to train and adapt models locally without relying on cloud infrastructure. A key innovation is its support for BitNet ternary quantized models, enabling highly efficient inference and training even on resource-constrained systems.