Awesome GitHub RepositoriesBatch Aggregators

StatsD is a metrics aggregator and UDP collection server that collects system counters and timers. It functions as a time-series data forwarder, receiving high-frequency metric updates via a lightweight line protocol and summarizing them before flushing the data to a backend. The project features a pluggable metrics backend framework, allowing aggregated statistics to be routed to various third-party monitoring services or time-series databases such as Graphite. It supports horizontal scaling and high availability through a proxy ring distribution system that forwards incoming packets across

Telegraf is a modular, cross-platform telemetry pipeline designed to collect, process, and route metrics from diverse infrastructure, applications, and hardware. It functions as a server-side middleware that normalizes heterogeneous data into a unified format, enabling consistent monitoring across complex environments. By utilizing a plugin-driven architecture, the agent manages the entire lifecycle of telemetry data from initial ingestion to final transmission. The project distinguishes itself through a declarative, configuration-driven execution model that allows users to define complex dat

Data-Juicer is an open-source framework for cleaning, filtering, deduplicating, and transforming multimodal datasets to prepare them for training large language and vision models. It functions as a distributed data pipeline engine that runs processing jobs across Ray clusters, handling billions of samples with automatic operator fusion and adaptive parallelism. The framework provides a library of operators that leverage large language models for semantic extraction, filtering, and data synthesis within processing pipelines. The project distinguishes itself through a YAML-based data recipe sys

Anomalib is a PyTorch-based library for visual anomaly detection, offering a modular framework, a comprehensive model zoo, and a benchmarking suite designed for industrial defect detection. It provides a wide range of algorithms—including generative, discriminative, teacher-student, and vision-language approaches—that support unsupervised, few-shot, and zero-shot settings. The library enables deployment through model export to ONNX and OpenVINO for edge devices, and includes a no-code web application for training and inference. It also features a command-line interface for orchestrating multi

MMF is a modular framework for building, training, and evaluating vision-and-language models. It provides a configuration-driven experiment system where model, dataset, and training parameters are defined through composable YAML files, alongside a curated model zoo of pretrained checkpoints for state-of-the-art multimodal architectures. The framework includes a multimodal dataset loader that downloads, processes, and batches vision-and-language data, and a vision-language model trainer supporting distributed training, mixed precision, and checkpoint-based resumption. The framework distinguish

Flashlight est une bibliothèque de machine learning en C++ et un framework de deep learning conçu pour construire et entraîner des réseaux de neurones. Il fonctionne comme une bibliothèque de manipulation de tenseurs et un moteur de différenciation automatique qui suit les opérations pour calculer les gradients via la rétropropagation pour l'optimisation des modèles. Le projet se distingue par son rôle de framework d'entraînement distribué, utilisant la synchronisation de gradient all-reduce et des environnements distribués pour mettre à l'échelle les charges de travail de machine learning sur plusieurs nœuds et appareils. Il dispose d'une interface mémoire agnostique au backend et d'une gestion basée sur RAII pour découpler les opérations sur tenseurs du matériel physique. Le framework couvre une large surface de capacités, incluant la construction d'architectures de réseaux de neurones avec des couches convolutionnelles, linéaires et récurrentes. Il fournit des utilitaires étendus pour l'algèbre tensorielle, la gestion et le batching de jeux de données, la sérialisation binaire versionnée pour les états de modèle, et des outils de surveillance pour suivre les métriques d'entraînement et l'utilisation de la mémoire.