Search Results for "throughput" - Page 9
Sort By:
Showing 502 open source projects for "throughput"
View related business solutions-
Gemini 3 and 200+ AI Models on One PlatformBuild, govern, and optimize agents and models with Gemini Enterprise Agent Platform.
-
Auth0 B2B Essentials: SSO, MFA, and RBAC Built InAuth0's B2B Essentials plan gives you everything you need to ship secure multi-tenant apps. Unlimited orgs, enterprise SSO, RBAC, audit log streaming, and higher auth and API limits included. Add on M2M tokens, enterprise MFA, or additional SSO connections as you scale.
-
1
TensorHouse
A collection of reference Jupyter notebooks and demo AI/ML application
TensorHouse is a scalable reinforcement learning (RL) platform that focuses on high-throughput experience generation and distributed training. It is designed to efficiently train agents across multiple environments and compute resources. TensorHouse enables flexible experiment management, making it suitable for large-scale RL experiments in both research and applied settings. -
2
DBD2
A multi-threaded, multi-database tcp-based database insertion app.
DBD2 inserts database records from TCP input. It is a companion project to Syslgod2 and an application in its own right. It ships with a backgrounding client for generic use. The client sends whatever information the user puts on the command-line to the back-end daemon via TCP. Upon successful transmission, the client exits. On failure, it backs off and retries until its life-time timer expires. The back-end daemon accepts data from Syslogd2 or its own client and inserts that data... -
3
SageMaker TensorFlow
SageMaker specific extensions to TensorFlow
...Please make sure to checkout the branch of sagemaker-tensorflow-extensions that matches your TensorFlow version. SageMaker Pipe Mode is a mechanism for providing S3 data to a training job via Linux fifos. Training programs can read from the fifo and get high-throughput data transfer from S3, without managing the S3 access in the program itself. -
4
CryoUtilities
A utility to improve performance and help manage storage on Steam Deck
...It provides tools to tweak memory management parameters such as swap size and swappiness, adjust HugePages and kernel memory behaviors, and free up space by cleaning leftover game data, shader caches, and compatibility data for uninstalled titles. The utilities aim to balance performance and system responsiveness, especially in gaming scenarios where constrained RAM and storage throughput can cause stutters or slow load times. The project includes an installer, an easy GUI launcher, and numerous toggles for Linux kernel parameters, and it abstracts many common tweaks that would otherwise require manual command-line intervention. -
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
OnnxStream
Lightweight inference library for ONNX files, written in C++
...The recommended minimum RAM/VRAM for Stable Diffusion 1.5 is typically 8GB. Generally, major machine learning frameworks and libraries are focused on minimizing inference latency and/or maximizing throughput, all of which at the cost of RAM usage. So I decided to write a super small and hackable inference library specifically focused on minimizing memory consumption: OnnxStream. OnnxStream is based on the idea of decoupling the inference engine from the component responsible for providing the model weights, which is a class derived from WeightsProvider. ... -
6
Zoekt
Fast trigram based code search
zoekt is a fast, scalable code search engine written in Go that builds compressed indexes (shards) for source repositories and serves low-latency regex and substring queries. It optimizes for developer workflows: refresh indexes from Git, search across many repos instantly, and jump into hits with surrounding context and file navigation. The indexer uses efficient n-gram dictionaries and posting lists to keep query latency low, while storing metadata (branch, language, repo) for precise... -
7
Punica
Serving multiple LoRA finetuned LLM as one
...The system includes specialized CUDA kernels that enable batched GPU operations across different LoRA models simultaneously. This design allows a single GPU cluster to host many task-specific models while maintaining high throughput and minimal latency. The architecture also includes scheduling mechanisms that coordinate requests from multiple tenants and distribute workloads efficiently across available resources. -
8
Apache Pegasus
A consistent and high-performance key-value store
A distributed key-value store optimized for low-latency and high-throughput applications, developed by Apache Incubator. -
9
NSQ
A realtime distributed messaging platform
NSQ is a realtime distributed messaging platform that is designed to scale, and can even handle billions of messages daily. It promotes distributed and decentralized topologies, allowing it high availability and fault tolerance along with guaranteed reliable message delivery. NSQ scales horizontally and is easy to configure and deploy. It is agnostic to data format, so messages can be in JSON, MsgPack, Protocol Buffers, or anything else. Official Go and Python libraries are available,... -
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.
-
10
LLaMA-MoE
Building Mixture-of-Experts from LLaMA with Continual Pre-training
LLaMA-MoE is an open-source project that builds mixture-of-experts language models from LLaMA through expert partitioning and continual pre-training. The repository is centered on making MoE research more accessible by offering smaller and more affordable models with only about 3.0 to 3.5 billion activated parameters, which helps reduce deployment and experimentation costs. Its architecture works by splitting LLaMA feed-forward networks into sparse experts and adding gating mechanisms so... -
11
RethinkDB
The open-source database for the realtime web
...RethinkDB can be used for a number of different things: building realtime trading and optimization engines; simplifying the data infrastructure in multiplayer games to produce low latency, high throughput realtime interactions; building reactive web and mobile apps with a lot less effort, and so much more. -
12
HPN-SSH is a series of performance patches for OpenSSH. By addressing network limitations and CPU limitations significant throughput performance can be realized. Gains of close to two orders of magnitude are possible on long fat network paths. The official git repo is now available at http://github.com/rapier1/openssh-portable. The Sourceforge repository should not be seen as the canonical repository for HPN-SSH. We will update it as we can but users should look to github to generate patches We also support Ubuntu packages. ...
-
13
KeyDB
A Multithreaded Fork of Redis
KeyDB is an incredibly fast NoSQL database, a high performance fork of Redis that can perform up to 5X faster than Redis and can be used as a drop in alternative. KeyDB is focused on multithreading, memory efficiency, and high throughput, with features and capabilities not readily available with Redis. KeyDB has gained quite a reputation for its exceptional performance and features. Apart from multithreading it offers such features as multi-master replication, persistence capabilities, horizontal and vertical scalability and direct backup to AWS S3 right out of the box. ... -
14
progress
Linux tool to show progress for cp, mv, dd, ... (formerly known as cv)
...Instead of modifying the original commands, the tool scans the system’s process information to detect active file operations and estimates their completion percentage, throughput, and remaining time. It offers a top-like monitoring mode that continuously updates the status of ongoing transfers, making it especially useful during large file operations where native feedback is limited. The utility works across Linux, FreeBSD, and macOS environments and is designed to remain extremely small and efficient. ... -
15
rathole
A lightweight and high-performance reverse proxy for NAT traversal
A secure, stable and high-performance reverse proxy for NAT traversal, written in Rust. rathole, like frp and ngrok, can help to expose the service on the device behind the NAT to the Internet, via a server with a public IP. High Performance Much higher throughput can be achieved than frp, and more stable when handling a large volume of connections. Low Resource Consumption Consumes much fewer memory than similar tools. See Benchmark. The binary can be as small as ~500KiB to fit the constraints of devices, like embedded devices as routers. Security Tokens of services are mandatory and service-wise. ... -
16
Medusa
Framework for Accelerating LLM Generation with Multiple Decoding Heads
Medusa is a framework aimed at accelerating the generation capabilities of Large Language Models (LLMs) by employing multiple decoding heads. This approach allows for parallel processing during text generation, significantly enhancing throughput and reducing response times. Medusa is designed to be simple to implement and integrates with existing LLM infrastructures, making it a practical solution for scaling LLM applications. -
17
LMAX Disruptor
High performance inter-thread messaging library
LMAX aims to be the fastest trading platform in the world. Clearly, in order to achieve this we needed to do something special to achieve very low-latency and high-throughput with our Java platform. Performance testing showed that using queues to pass data between stages of the system was introducing latency, so we focused on optimising this area. The Disruptor is the result of our research and testing. We found that cache misses at the CPU-level, and locks requiring kernel arbitration are both extremely costly, so we created a framework which has "mechanical sympathy" for the hardware it’s running on, and that’s lock-free. ... -
18
Dragonboat
A feature complete and high performance multi-group Raft library in Go
...It also appears to clients as a single entity with strong data consistency always provided. All Raft replicas can be used to handle read requests for aggregated read throughput. Dragonboat handles all technical difficulties associated with Raft to allow users to just focus on their application domains. It is also very easy to use, our step-by-step examples can help new users to master it in half an hour. Easy to use pure-Go APIs for building Raft based applications. Feature complete and scalable multi-group Raft implementation. ... -
19
FastViT
This repository contains the official implementation of research
FastViT is an efficient vision backbone family that blends convolutional inductive biases with transformer capacity to deliver strong accuracy at mobile and real-time inference budgets. Its design pursues a favorable latency-accuracy Pareto curve, targeting edge devices and server scenarios where throughput and tail latency matter. The models use lightweight attention and carefully engineered blocks to minimize token mixing costs while preserving representation power. Training and inference recipes highlight straightforward integration into common vision tasks such as classification, detection, and segmentation. The codebase provides reference implementations and checkpoints that make it easy to evaluate or fine-tune on downstream datasets. ... -
20
FastQC
A quality control analysis tool for high throughput sequencing data
FastQC is a quality control analysis tool designed to spot potential problems in high throughput sequencing datasets. Its goal is to provide a simple way by which to check the quality of raw sequence data coming from high throughput sequencing pipelines. It does this by running a modular set of analyses on one or more raw sequence files in fastq or bam format. It then produces a report summarizing the results, and highlighting any areas where the library may appear unusual. ... -
21
FFCV
Fast Forward Computer Vision (and other ML workloads!)
ffcv is a drop-in data loading system that dramatically increases data throughput in model training. From gridding to benchmarking to fast research iteration, there are many reasons to want faster model training. Below we present premade codebases for training on ImageNet and CIFAR, including both (a) extensible codebases and (b) numerous premade training configurations. -
22
FasterTransformer
Transformer related optimization, including BERT, GPT
FasterTransformer is a high-performance inference library designed to accelerate transformer-based models such as BERT, GPT, and T5 on NVIDIA GPUs. It provides optimized implementations of transformer encoder and decoder layers using CUDA, cuBLAS, and custom kernels to maximize throughput and minimize latency. The library supports multiple deep learning frameworks, including TensorFlow, PyTorch, and Triton, allowing developers to integrate it into existing pipelines without major changes. It includes advanced optimization techniques such as mixed precision, tensor parallelism, and efficient memory management, enabling large models to run across multiple GPUs and nodes. ... -
23
ixy-languages
A high-speed network driver written in C, Rust, C++, Go, C#, Java
ixy-languages is a repository exploring the implementation of the ixy network driver (originally written in C) in multiple programming languages, showing how the same core logic can be expressed across language boundaries. The ixy driver is a minimal DPDK-based user-space NIC driver intended for education, demonstration, and controlled experimentation. This project reimplements the ixy driver architecture in Rust, Go, C++, Zig, and possibly other languages, maintaining the same driver... -
24
SnappyData
Memory optimized analytics database, based on Apache Spark
SnappyData (aka TIBCO ComputeDB) is a distributed, in-memory optimized analytics database. SnappyData delivers high throughput, low latency, and high concurrency for a unified analytics workload. By fusing an in-memory hybrid database inside Apache Spark, it provides analytic query processing, mutability/transactions, access to virtually all big data sources and stream processing all in one unified cluster. One common use case for SnappyData is to provide analytics at interactive speeds over large volumes of data with minimal or no pre-processing of the dataset. ... -
25
LightSeq
A High Performance Library for Sequence Processing and Generation
Lightseq is a high-performance library focused on efficient inference and training for deep learning models, especially large language models (LLMs) and transformer-based architectures. Its goal is to optimize both memory usage and computational throughput, enabling faster training or inference on limited hardware while maintaining model quality. Lightseq provides optimized CUDA kernels, quantization strategies, and runtime optimizations tailored for transformer operations — which often are bottlenecks in conventional frameworks — thereby reducing memory footprint, improving speed, and making deployment of large-scale models more accessible. ...
