Search Results for "network performance"
Sort By:
Showing 92 open source projects for "network performance"
View related business solutions-
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.
-
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
1
Front-End Performance Checklist
The only Front-End Performance Checklist that runs faster
Front-End-Performance-Checklist is a comprehensive, developer-friendly guide that consolidates the most impactful client-side performance practices into a single, scannable resource. It frames performance as a front-end responsibility and turns broad principles into concrete, verifiable checks you can apply before shipping. The checklist is organized by areas such as HTML, CSS, JavaScript, fonts, images, and network delivery, so teams can tackle bottlenecks systematically. ... -
2
oneDNN
oneAPI Deep Neural Network Library (oneDNN)
This software was previously known as Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN) and Deep Neural Network Library (DNNL). oneAPI Deep Neural Network Library (oneDNN) is an open-source cross-platform performance library of basic building blocks for deep learning applications. oneDNN is part of oneAPI. The library is optimized for Intel(R) Architecture Processors, Intel Processor Graphics and Xe Architecture graphics. oneDNN has experimental support for the following architectures: Arm* 64-bit Architecture (AArch64), NVIDIA* GPU, OpenPOWER* Power ISA (PPC64), IBMz* (s390x), and RISC-V. oneDNN is intended for deep learning applications and framework developers interested in improving application performance on Intel CPUs and GPUs. ... -
3
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, embedded, or automotive product platforms. ... -
4
XNNPACK
High-efficiency floating-point neural network inference operators
XNNPACK is a highly optimized, low-level neural network inference library developed by Google for accelerating deep learning workloads across a variety of hardware architectures, including ARM, x86, WebAssembly, and RISC-V. Rather than serving as a standalone ML framework, XNNPACK provides high-performance computational primitives—such as convolutions, pooling, activation functions, and arithmetic operations—that are integrated into higher-level frameworks like TensorFlow Lite, PyTorch Mobile, ONNX Runtime, TensorFlow.js, and MediaPipe. ... -
Save Up to 91% on Cloud Compute With Spot VMsRun batch jobs at 60-91% off with Spot VMs. Long-running workloads get automatic discounts with sustained use.
-
5
Napkin Math
Techniques and numbers for estimating system's performance
Napkin Math is a technical reference project for estimating software system performance from first principles. It collects practical numbers, benchmark-style measurements, and mental models that help engineers make fast back-of-the-envelope calculations. The project is useful for questions like how much memory throughput matters, how long storage operations may take, what network latency to expect, or how expensive logging could become at high request volume. -
6
Size Limit
Calculate the real cost to run your JS app or lib
Size Limit is a JavaScript performance budget tool that measures the real cost of your JavaScript bundle and prevents regressions by enforcing limits in CI. It calculates not just raw bundle size, but also download and execution time under configurable network conditions, giving a more realistic sense of what users experience. The tool is modular: it offers a CLI and multiple plugins (file, webpack, time) plus presets tailored to different use cases, from big single-page apps to small npm libraries. ... -
7
ncnn
High-performance neural network inference framework for mobile
ncnn is a high-performance neural network inference computing framework designed specifically for mobile platforms. It brings artificial intelligence right at your fingertips with no third-party dependencies, and speeds faster than all other known open source frameworks for mobile phone cpu. ncnn allows developers to easily deploy deep learning algorithm models to the mobile platform and create intelligent APPs. -
8
warp-yg
Warp multi-function one-click script, supports warp-go and wgcf
warp-yg is a script-based toolkit designed to automate the deployment and optimization of Cloudflare WARP networking configurations for enhanced privacy and performance. It focuses on simplifying the integration of WireGuard-based WARP connections into proxy environments, allowing users to route traffic through optimized Cloudflare endpoints. The project includes functionality for selecting optimal endpoints and improving connection speed by dynamically identifying efficient routes. It is often used in conjunction with other proxy tools to enhance reliability and bypass network restrictions by leveraging Cloudflare’s global infrastructure. ... -
9
RustDesk Server Program
Self-host your own RustDesk server
...By running your own server, you retain control over connection metadata and can operate entirely within your organization’s perimeter. The project targets simplicity of deployment while maintaining performance characteristics suitable for interactive screen sharing and file transfer. It supports common operational needs such as configuring ports, authentication modes, and relay behavior to match diverse network constraints. Together with RustDesk clients, it offers a fully open alternative to proprietary remote-access ecosystems with an emphasis on privacy and self-custody. -
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.
-
10
Gen.jl
A general-purpose probabilistic programming system
...But it also lets users migrate parts of their model or inference algorithm to specialized modeling languages for which it can generate especially fast code. Users can also hand-code parts of their models that demand better performance. Neural network inference is fast, but can be inaccurate on out-of-distribution data, and requires expensive training. -
11
Swoole
Coroutine-based concurrency library for PHP
...You can use sync or async, coroutine, fiber API to write the applications or create thousands of light weight fibers within one Linux process. Swoole PHP network framework enhances the efficiency of development team. The network layer in Swoole is event-based and takes full advantage of the underlying epoll/kqueue implementation, making it really easy to serve millions of requests. Swoole 4.x uses a brand new engine kernel and now it has a full-time developer team, so we are entering an unprecedented period in PHP history which offers a unique possibility for rapid evolution. -
12
libfabric
AWS Libfabric
The Open Fabrics Interfaces (OFI) is a framework focused on exporting fabric communication services to applications. Libfabric pre-built binaries may be available from other sources, such as Linux distributions. Elastic Fabric Adapter (EFA) is a network interface for Amazon EC2 instances that enables customers to run applications requiring high levels of inter-node communications at scale on AWS. Its custom-built operating system (OS) bypass hardware interface enhances the performance of inter-instance communications, which is critical to scaling these applications. With EFA, High Performance Computing (HPC) applications using the Message Passing Interface (MPI) and Machine Learning (ML) applications using NVIDIA Collective Communications Library (NCCL) can scale to thousands of CPUs or GPUs. ... -
13
libdatachannel
C/C++ WebRTC network library featuring Data Channels, Media Transport
libdatachannel is a C++ library that implements WebRTC DataChannels and ICE transports, enabling peer-to-peer communication without relying on media components. It is ideal for developers who want efficient, low-latency P2P communication for data transmission in IoT, multiplayer games, decentralized apps, or custom signaling architectures. Built for performance and minimalism, it allows fine-grained control over STUN, TURN, DTLS, and SCTP layers, with a clean and modern C++ interface. -
14
doc.rustdesk.com
Document of RustDesk
...The project treats documentation as code, enabling version control, community contributions, and swift iteration alongside product releases. It also provides best practices around performance tuning, authentication choices, and network topology so organizations can run RustDesk confidently at scale. -
15
RustDesk Server PRO
Some scripts for RustDesk Server Pro are hosted here
...It encompasses the components required to broker, relay, and supervise connections while adding administrative layers suitable for regulated or large environments. Organizations can standardize how clients authenticate, how sessions are permitted and audited, and how data paths are routed under diverse network constraints. The server emphasizes reliability for interactive use cases like remote control, file transfer, and support workflows, even when clients sit behind strict NAT or firewall rules. It aims to balance performance with privacy by letting companies retain custody over metadata and configuration within their own perimeter. ... -
16
Amazon EC2 Instance Selector
A CLI tool and go library which recommends instance types
...Instance Selector helps you select compatible instance types for your application to run on. The command-line interface can be passed resource criteria like vcpus, memory, network performance, and much more and then return the available, matching instance types. If you are using spot instances to save on costs, it is a best practice to use multiple instances types within your auto-scaling group (ASG) to ensure your application doesn't experience downtime due to one instance type being interrupted. Instance Selector will help to find a set of instance types that your application can run on. -
17
Workbox
JavaScript libraries for Progressive Web Apps
Workbox is a set of libraries that can power a production-ready service worker for your Progressive Web App. Stop waiting on the network! You can improve your web app's performance by caching and serving your files, powered by a service worker. Even on an unreliable connection, your web app can still work using the right runtime caching strategies. Looking to build a progressive web app? Workbox makes it easy to create an offline first experience. Workbox is a library that bakes in a set of best practices and removes the boilerplate every developer writes when working with service workers. ... -
18
libhv
Network library for developing TCP/UDP/SSL/HTTP/WebSocket/MQTT client
Like libevent, libev, and libuv, libhv provides event loop with non-blocking IO and timer, but simpler api and richer protocols. Cross-platform (Linux, Windows, MacOS, BSD, Solaris, Android, iOS) High-performance EventLoop (IO, timer, idle, custom) TCP/UDP client/server/proxy. TCP supports heartbeat, reconnect, upstream, MultiThread-safe write and close, etc. Built-in common unpacking modes (FixedLength, Delimiter, LengthField) RUDP support: WITH_KCP. SSL/TLS support: (via WITH_OPENSSL or... -
19
Opacus
Training PyTorch models with differential privacy
Opacus is a library that enables training PyTorch models with differential privacy. It supports training with minimal code changes required on the client, has little impact on training performance, and allows the client to online track the privacy budget expended at any given moment. Vectorized per-sample gradient computation that is 10x faster than micro batching. Supports most types of PyTorch models and can be used with minimal modification to the original neural network. Open source, modular API for differential privacy research. ... -
20
ProxyAdmin
Proxy is a high-performance, full-function http proxy, https proxy
ProxyAdmin Free is a web-based management console for the goproxy networking and proxy server. It provides a graphical alternative to managing goproxy entirely through command-line arguments. Administrators can configure HTTP and HTTPS proxies, SOCKS5 services, internal network tunneling, and other supported proxy modes. The interface also exposes remote-access features such as VNC and Web-SSH alongside custom service configuration. Logging and debug views make it easier to inspect running... -
21
Python Outlier Detection
A Python toolbox for scalable outlier detection
PyOD is a comprehensive and scalable Python toolkit for detecting outlying objects in multivariate data. This exciting yet challenging field is commonly referred as outlier detection or anomaly detection. PyOD includes more than 30 detection algorithms, from classical LOF (SIGMOD 2000) to the latest COPOD (ICDM 2020) and SUOD (MLSys 2021). Since 2017, PyOD [AZNL19] has been successfully used in numerous academic researches and commercial products [AZHC+21, AZNHL19]. PyOD has multiple neural... -
22
Ruma
A set of Rust crates for interacting with the Matrix chat network
Matrix is an open specification for an online communication protocol. It includes all the features you'd expect from a modern chat platform including instant messaging, group chats, audio and video calls, searchable message history, synchronization across all your devices, and end-to-end encryption. Matrix is federated, so no single company controls the system or your data. You can use an existing server you trust or run your own, and the servers synchronize messages seamlessly. Learn more... -
23
Lettuce
Advanced Java Redis client for thread-safe sync, async, etc.
Build elastic data access. Lettuce is a scalable Redis client for building non-blocking Reactive applications. Lettuce is a fully non-blocking Redis client built with netty providing Reactive, Asynchronous and Synchronous Data Access. Lettuce provides asynchronous API with RedisFuture (CompletionStage) and Reactive types Flux [N] and Mono [0|1]. Low-latency communication, backpressure-enabled network engine for NIO TCP, epoll TCP and Unix Domain Sockets. Reactive Streaming is fully... -
24
MirageOS
MirageOS is a library operating system that constructs unikernels
A programming framework for building type-safe, modular systems. MirageOS is a library operating system that constructs unikernels for secure, high-performance network applications across a variety of cloud computing and mobile platforms. Code can be developed on a normal OS such as Linux or macOS, and then compiled into a fully standalone, specialized unikernel that runs under a Xen or KVM hypervisor. This lets your services run more efficiently, securely and with finer control than with a full conventional software stack. -
25
RSocket
Java implementation of RSocket
Application protocol providing Reactive Streams semantics. RSocket provides a protocol for Reactive Streams semantics between client-server, and server-server communication. RSocket is a binary protocol for use on byte stream transports such as TCP, WebSockets, and Aeron. RSocket is intended to be consumed via one of the various implementation libraries which implement the RSocket Protocol. By default to make RSocket easier to use it copies the incoming Payload. Copying the payload comes at...
