Search Results for "throughput"
Sort By:
Showing 70 open source projects for "throughput"
View related business solutions-
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.
-
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
1
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. ... -
2
RTP-LLM
Alibaba's high-performance LLM inference engine for diverse apps
RTP-LLM is an open-source large language model inference acceleration engine developed by Alibaba to provide high-performance serving infrastructure for modern LLM deployments. The system focuses on improving throughput, latency, and resource utilization when running large models in production environments. It achieves this by implementing optimized GPU kernels, batching strategies, and memory management techniques tailored for transformer inference workloads. The framework is designed for large-scale AI services and is already used internally across several Alibaba platforms such as Taobao, Amap, and other business systems that rely on conversational or search-related AI services. ... -
3
D++
C++ Discord API Bot Library - D++ is Lightweight and scalable
D++ is a lightweight and simple library for Discord written in modern C++. It is designed to cover as much of the API specification as possible and to have an incredibly small memory footprint, even when caching large amounts of data. It is created by the developer of TriviaBot and contributed to by a dedicated team of developers. -
4
PikiwiDB
Pika is a Redis-Compatible database
A high-performance, distributed key-value database inspired by Redis but designed for large-scale cloud-native environments. -
Streamline Azure Security with Palo Alto Networks VM-SeriesImprove your security posture and reduce incident response time. Use the VM-Series to natively analyze Azure traffic and dynamically drive policy updates based on workload changes.
-
5
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. On very compute-bound settings, it can reach up to ~660 TFLOPS on H800 SXM5 hardware, while in memory-bound configurations it can push memory throughput to ~3000 GB/s. ... -
6
EnvPool
C++-based high-performance parallel environment execution engine
EnvPool is a fast, asynchronous, and parallel RL environment library designed for scaling reinforcement learning experiments. Developed by SAIL at Singapore, it leverages C++ backend and Python frontend for extremely high-speed environment interaction, supporting thousands of environments running in parallel on a single machine. It's compatible with Gymnasium API and RLlib, making it suitable for scalable training pipelines. -
7
Dragonfly
A modern replacement for Redis and Memcached
...Designed to fully utilize the power of modern cloud hardware and deliver on the data demands of modern applications, Dragonfly frees developers from the limits of traditional in-memory data stores. The power of modern cloud hardware can never be realized with legacy software. Dragonfly is optimized for modern cloud computing, delivering 25x more throughput and 12x lower snapshotting latency when compared to legacy in-memory data stores like Redis, making it easy to deliver the real-time experience your customers expect. Scaling Redis workloads is expensive due to their inefficient, single-threaded model. Dragonfly is far more compute and memory efficient, resulting in up to 80% lower infrastructure costs. ... -
8
frugally-deep
A lightweight header-only library for using Keras (TensorFlow) models
...Utterly ignores even the most powerful GPU in your system and uses only one CPU core per prediction. Quite fast on one CPU core, and you can run multiple predictions in parallel, thus utilizing as many CPUs as you like to improve the overall prediction throughput of your application/pipeline. -
9
QuestDB
An open source SQL database designed to process time series data
QuestDB is a high-performance, open-source SQL database for applications in financial services, IoT, machine learning, DevOps and observability. It includes endpoints for PostgreSQL wire protocol, high-throughput schema-agnostic ingestion using InfluxDB Line Protocol, and a REST API for queries, bulk imports, and exports. QuestDB implements ANSI SQL with native extensions for time-oriented language features. These extensions make it simple to correlate data from multiple sources using relational and time series joins. QuestDB achieves high performance from a column-oriented storage model, massively-parallelized vector execution, SIMD instructions, and various low-latency techniques. ... -
Build Securely on Azure with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
10
Bowtie 2
A fast and sensitive gapped read aligner
...It is widely used in bioinformatics pipelines for RNA-seq, DNA-seq, metagenomics, variant analysis, and other sequencing-based research tasks. Overall, Bowtie 2 remains a foundational command-line tool for high-throughput sequence alignment and reproducible computational biology workflows. -
11
bitnet.cpp
Official inference framework for 1-bit LLMs
...BitNet is built to scale across architectures, with configurable kernels and tiling strategies that adapt to different hardware, and it supports large models with impressive throughput even on modest resources. -
12
Zvec
A lightweight, lightning-fast, in-process vector database
...Developed by Alibaba’s Tongyi Lab, it positions itself as the “SQLite of vector databases” by being easy to integrate, minimal in dependencies, and capable of handling high throughput with low latency on edge devices or small systems. Zvec excels at approximate nearest neighbor search and retrieval tasks that power features like semantic search, recommendation systems, and retrieval-augmented generation (RAG) setups. Its performance benchmarks show it achieving high queries-per-second and fast index build times compared to similar tools. ... -
13
Marl
A hybrid thread / fiber task scheduler written in C++ 11
marl is a lightweight C++ job system that schedules tasks on a pool of worker threads and runs them using cooperative fibers for high throughput. By decoupling “tasks” from OS threads, it minimizes context switches and lets workloads with fine-grained synchronization scale efficiently. The API is intentionally small—post tasks, wait on fences, and express dependencies—so you can retrofit it into existing engines without adopting a heavyweight framework. Under the hood, fibers allow tasks to yield while waiting, keeping cores busy without blocking threads. ... -
14
RobotsTxt
The repository contains Google's robots.txt parser
This is a high-performance, production-tested library for parsing and evaluating robots.txt rules against crawler user agents. It implements the core semantics of the Robots Exclusion Protocol: user-agent sections, Allow/Disallow directives, wildcard handling, and precedence rules. The code is optimized for speed and low memory so large crawls can evaluate millions of URLs quickly. It also focuses on correctness—edge cases like overlapping patterns and longest-match resolution are handled... -
15
OpenMLDB
OpenMLDB is an open-source machine learning database
...However, a feature engineering script developed by data scientists (Python scripts in most cases) cannot be directly deployed into production for online inference because it usually cannot meet the engineering requirements, such as low latency, high throughput and high availability. -
16
OpenVINO Model Server
A scalable inference server for models optimized with OpenVINO
...It’s implemented in C++ for scalability and efficiency, making it suitable for both edge and cloud deployments where inference workloads must be reliable and high throughput. The server exposes model inference via standard network protocols like REST and gRPC, allowing any client that speaks those protocols to request predictions remotely, abstracting away the complexity of where and how the model runs. It supports model deployment in diverse environments including Docker, bare-metal machines, and Kubernetes clusters, and is especially useful in microservices architectures where AI services need to scale independently. ... -
17
TensorStore
Library for reading and writing large multi-dimensional arrays
...Transactional semantics allow atomic updates and consistent snapshots, which is essential for large, shared datasets used by ML and scientific workflows. The library is engineered for scalability—background caching, chunk sharding, and retryable operations keep throughput high even over unreliable networks. With language bindings, it fits into Python-heavy analysis pipelines while retaining a fast C++ core. -
18
fairseq2
FAIR Sequence Modeling Toolkit 2
fairseq2 is a modern, modular sequence modeling framework developed by Meta AI Research as a complete redesign of the original fairseq library. Built from the ground up for scalability, composability, and research flexibility, fairseq2 supports a broad range of language, speech, and multimodal content generation tasks, including instruction fine-tuning, reinforcement learning from human feedback (RLHF), and large-scale multilingual modeling. Unlike the original fairseq—which evolved into a... -
19
Isaac ROS Visual SLAM
Visual SLAM/odometry package based on NVIDIA-accelerated cuVSLAM
Discover a faster, easier way to build advanced AI robotics applications with the NVIDIA Isaac™ ROS collection of accelerated computing packages and AI models, bringing NVIDIA acceleration to ROS developers everywhere. Isaac ROS Visual SLAM provides a high-performance, best-in-class ROS 2 package for VSLAM (visual simultaneous localization and mapping). This package uses one or more stereo cameras and optionally an IMU to estimate odometry as an input to navigation. It is GPU-accelerated to... -
20
DALI
A GPU-accelerated library containing highly optimized building blocks
...DALI addresses the problem of the CPU bottleneck by offloading data preprocessing to the GPU. Additionally, DALI relies on its own execution engine, built to maximize the throughput of the input pipeline. -
21
qvac-fabric-llm.cpp
QVAC Fabric: cross-platform LLM inference and fine-tuning
qvac-fabric-llm.cpp is a cross-platform large language model inference and fine-tuning engine built as an advanced fork of llama.cpp, designed to run efficiently across desktops, mobile devices, and heterogeneous GPU environments. 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... -
22
Mooncake
Mooncake is the serving platform for Kimi
...Mooncake also introduces distributed key-value cache storage that allows inference systems to reuse previously computed attention states, significantly improving throughput in large-scale deployments. The system supports advanced networking technologies such as RDMA and NVMe over Fabric, enabling high-speed communication across clusters. -
23
XLS
XLS: Accelerated HW Synthesis
...XLS also provides tooling for pipelining, state insertion, and formal equivalence checks between different stages, giving developers confidence as designs evolve. The result is a productive path from high-level specification to real hardware, without giving up control over latency, throughput, and area trade-offs. -
24
RESTinio
HTTP/WebSocket server C++14 library
RESTinio is a header-only C++14 library that gives you an embedded HTTP/WebSocket server. It is based on the standalone version of ASIO and is targeted primarily for the asynchronous processing of HTTP requests. Since v.0.4.1 Boost::ASIO (1.66 or higher) is also supported. Consider the task of writing a C++ application that must support some REST API, RESTinio represents our solution for that task. Server runs on the main thread, and responds to all requests with a hello-world message. Of... -
25
Apache brpc
Industrial-grade RPC framework used throughout Baidu
Apache brpc is an industrial-grade RPC framework for building reliable and high-performance services. Apache brpc (incubating) is an effort undergoing Incubation at The Apache Software Foundation (ASF), sponsored by the Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not...
