Search Results for "gpu"
Sort By:
Showing 101 open source projects for "gpu"
View related business solutions-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
1
cuda-oxide
cuda-oxide is an experimental Rust-to-CUDA compiler
...Its main value is giving Rust developers a more direct path into NVIDIA GPU kernels while preserving familiar Rust syntax and tooling concepts. -
2
jamesob's guide to running SOTA LLMs
Everything I know about running LLMs locally
jamesob's guide to running SOTA LLMs is a practical guide and configuration repository for running high-end language models on local hardware. It documents one developer’s local LLM setup, including hardware choices, GPU layout, storage, PCIe switches, kernel settings, and serving workflows. The repository compares budget levels ranging from dual RTX 3090 systems to high-end multi-GPU workstations with very large VRAM pools. It includes ready-to-run serving configurations for selected models and local speech-to-text workloads. The guide focuses on real deployment details such as Docker containers, model weight storage, GPU peer-to-peer behavior, and agentic workload performance. ... -
3
CuPy
A NumPy-compatible array library accelerated by CUDA
CuPy is an open source implementation of NumPy-compatible multi-dimensional array accelerated with NVIDIA CUDA. It consists of cupy.ndarray, a core multi-dimensional array class and many functions on it. CuPy offers GPU accelerated computing with Python, using CUDA-related libraries to fully utilize the GPU architecture. According to benchmarks, it can even speed up some operations by more than 100X. CuPy is highly compatible with NumPy, serving as a drop-in replacement in most cases. CuPy is very easy to install through pip or through precompiled binary packages called wheels for recommended environments. ... -
4
Khronos KTX
KTX (Khronos Texture) Library and Tools
KTX-Software is a suite of tools and libraries for working with Khronos Texture (KTX) files, designed and maintained by the Khronos Group. KTX is a container format for storing textures that are optimized for GPU upload, supporting modern formats like Basis Universal and ASTC. This repository includes tools for creating, validating, inspecting, and converting KTX and KTX2 files, making it essential for developers working in 3D engines, games, and visualization tools where texture streaming and compression are key. -
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
CUDA Core Compute Libraries (CCCL)
CUDA Core Compute Libraries
...By unifying these components, CCCL reduces duplication and improves developer productivity while maintaining performance across different GPU architectures. -
6
cuDF
GPU DataFrame Library
...The RAPIDS suite of open-source software libraries aims to enable the execution of end-to-end data science and analytics pipelines entirely on GPUs. It relies on NVIDIA® CUDA® primitives for low-level compute optimization but exposing that GPU parallelism and high-bandwidth memory speed through user-friendly Python interfaces. -
7
libplacebo
Official mirror of libplacebo
libplacebo is a flexible, high-performance graphics library built on top of Vulkan, designed to provide reusable GPU-accelerated components for media applications. It originated as a core part of the rendering pipeline for the mpv media player and has since grown into a standalone library used for tone mapping, dithering, color space conversion, and more. libplacebo is ideal for developers looking to integrate sophisticated video rendering and post-processing into their own applications with full control over shaders and rendering stages. -
8
Faiss
Library for efficient similarity search and clustering dense vectors
...It also contains supporting code for evaluation and parameter tuning. Faiss is written in C++ with complete wrappers for Python/numpy. Some of the most useful algorithms are implemented on the GPU. It is developed by Facebook AI Research. Faiss contains several methods for similarity search. It assumes that the instances are represented as vectors and are identified by an integer, and that the vectors can be compared with L2 (Euclidean) distances or dot products. Vectors that are similar to a query vector are those that have the lowest L2 distance or the highest dot product with the query vector. ... -
9
DGL
Python package built to ease deep learning on graph
...We also want to make the combination of graph based modules and tensor based modules (PyTorch or MXNet) as smooth as possible. DGL provides a powerful graph object that can reside on either CPU or GPU. It bundles structural data as well as features for a better control. We provide a variety of functions for computing with graph objects including efficient and customizable message passing primitives for Graph Neural Networks. -
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.
-
10
MuJoCo Playground
An open source library for GPU-accelerated robot learning
MuJoCo Playground, developed by Google DeepMind, is a GPU-accelerated suite of simulation environments for robot learning and sim-to-real research, built on top of MuJoCo MJX. It unifies a range of control, locomotion, and manipulation tasks into a consistent and scalable framework optimized for JAX and Warp backends. The project includes classic control benchmarks from dm_control, advanced quadruped and bipedal locomotion systems, and dexterous as well as non-prehensile manipulation setups. ... -
11
DeepEP
DeepEP: an efficient expert-parallel communication library
DeepEP is a communication library designed specifically to support Mixture-of-Experts (MoE) and expert parallelism (EP) deployments. Its core role is to implement high-throughput, low-latency all-to-all GPU communication kernels, which handle the dispatching of tokens to different experts (or shards) and then combining expert outputs back into the main data flow. Because MoE architectures require routing inputs to different experts, communication overhead can become a bottleneck — DeepEP addresses that by providing optimized GPU kernels and efficient dispatch/combining logic. ... -
12
PortableGL
An implementation of OpenGL 3.x-ish in clean C
PortableGL is a single-header, software-only implementation of a subset of OpenGL (specifically the GL 2.1 pipeline), designed to run entirely on the CPU. This lightweight graphics library allows OpenGL-style rendering without GPU acceleration, making it ideal for educational use, debugging, embedded systems, and retro-style software rendering. Because it mirrors OpenGL syntax and design, it can act as a drop-in CPU renderer for testing or deploying 3D graphics on platforms without GPU support. -
13
Shumai
Fast Differentiable Tensor Library in JavaScript & TypeScript with Bun
...It can automatically leverage GPU acceleration on Linux (via CUDA) and CPU computation on macOS. -
14
webgl-plot
A high-Performance real-time 2D plotting library based on native WebGL
...Unlike traditional canvas or SVG-based charting libraries, webgl-plot is optimized for streaming and dynamic updates, making it ideal for oscilloscope-style data, biomedical signals, or any application where data updates hundreds of times per second. Its minimal memory footprint and GPU acceleration ensure excellent performance even with tens of thousands of data points, and its simple API allows developers to get started quickly. -
15
Images.jl
An image library for Julia
...Julia is well-suited to image processing because it is a modern and elegant high-level language that is a pleasure to use, while also allowing you to write "inner loops" that compile to efficient machine code (i.e., it is as fast as C). Julia supports multithreading and, through add-on packages, GPU processing. JuliaImages is a collection of packages specifically focused on image processing. It is not yet as complete as some toolkits for other programming languages, but it has many useful algorithms. It is focused on clean architecture and is designed to unify "machine vision" and "biomedical 3d image processing" communities. -
16
RLax
Library of JAX-based building blocks for reinforcement learning agents
...It supports both on-policy and off-policy learning, as well as value-based, policy-based, and model-based approaches. RLax is fully JIT-compilable with JAX, enabling high-performance execution across CPU, GPU, and TPU backends. The library implements tools for Bellman equations, return distributions, general value functions, and policy optimization in both continuous and discrete action spaces. It integrates seamlessly with DeepMind’s Haiku (for neural network definition) and Optax (for optimization), making it a key component in modular RL pipelines. -
17
Theseus
A library for differentiable nonlinear optimization
...Because solves are differentiable, you can backpropagate through optimization to learn cost weights, feature extractors, or initialization networks end-to-end. The implementation supports batched optimization on GPU, robust losses, damping strategies, and custom factors, making it practical for real-time systems. Helper packages provide geometry primitives and utilities for composing priors, relative constraints, and measurement models. Theseus bridges the gap between classical optimization and deep learning, enabling hybrid systems that learn components. -
18
Face Alignment
2D and 3D Face alignment library build using pytorch
...However, the users can alternatively use dlib, BlazeFace, or pre-existing ground truth bounding boxes. While not required, for optimal performance(especially for the detector) it is highly recommended to run the code using a CUDA-enabled GPU. While here the work is presented as a black box, if you want to know more about the intrisecs of the method please check the original paper either on arxiv or my webpage. -
19
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... -
20
GPUPixel
Real-time image and video processing library similar to GPUImage
GPUPixel is a real-time image and video processing library written in C++11, based on OpenGL/ES. It offers functionalities similar to GPUImage, including built-in beauty filters, enabling efficient processing and rendering of visual effects on images and videos. -
21
FlashMLA
FlashMLA: Efficient Multi-head Latent Attention Kernels
FlashMLA is a high-performance decoding kernel library designed especially for Multi-Head Latent Attention (MLA) workloads, targeting NVIDIA Hopper GPU architectures. It provides optimized kernels for MLA decoding, including support for variable-length sequences, helping reduce latency and increase throughput in model inference systems using that attention style. The library supports both BF16 and FP16 data types, and includes a paged KV cache implementation with a block size of 64 to efficiently manage memory during decoding. ... -
22
Floem
A native Rust UI library with fine-grained reactivity
Floem is a cross-platform GUI framework for Rust. It aims to be extremely performant while providing world-class developer ergonomics. Supporting both GPU and CPU rendering, Floem gives you performance that's closest to bare metal. Also primitives are provided to help the developer to write performant UI code without too much effect. -
23
FairChem
FAIR Chemistry's library of machine learning methods for chemistry
...Tasks span heterogeneous domains—catalysis (OC20-style), inorganic materials (OMat), molecules (OMol), MOFs (ODAC), and molecular crystals (OMC)—allowing one model family to serve many simulations. The README provides quick paths for pulling models (e.g., via Hugging Face access), then running energy/force predictions on GPU or CPU. -
24
Tracy Profiler
Frame profiler
...Tracy supports profiling CPU (Direct support is provided for C, C++, Lua and Python integration. At the same time, third-party bindings to many other languages exist on the internet, such as Rust, Zig, C#, OCaml, Odin, etc.), GPU (All major graphic APIs: OpenGL, Vulkan, Direct3D 11/12, OpenCL.), memory allocations, locks, context switches, automatically attribute screenshots to captured frames, and much more. -
25
TensorRT
C++ library for high performance inference on NVIDIA GPUs
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference. It includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for deep learning inference applications. TensorRT-based applications perform up to 40X faster than CPU-only platforms during inference. 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,...