38 repository-uri
Techniques for grouping multiple small data operations into a single larger request to increase throughput.
Distinct from Obsolete Entry Clearing: The candidates focus on log inspection or cleanup; this is a performance optimization for processing multiple log entries together.
Explore 38 awesome GitHub repositories matching data & databases · Request Batching. Refine with filters or upvote what's useful.
Hystrix is a latency and fault tolerance library designed to prevent cascading failures in distributed systems. It functions as a circuit breaker implementation that monitors failure thresholds and opens circuits to isolate remote calls when downstream services degrade. The project distinguishes itself by providing multiple isolation mechanisms, utilizing dedicated thread pools and semaphores to ensure that latency in one dependency does not saturate the entire system. It also features a request collapsing and batching engine that groups concurrent calls into single executions to reduce the t
Groups multiple concurrent calls into a single batch execution to reduce the total load on downstream systems.
FoundationDB is an ACID-compliant distributed transactional key-value store. It functions as a scalable database engine that ensures strict serializability and data consistency across a cluster of servers using a shared-nothing architecture. The system is distinguished by its multi-region replication capabilities, allowing data to be synchronized across different datacenters for high availability and disaster recovery. It utilizes optimistic concurrency control to manage distributed transactions and employs a majority-based coordination system to maintain cluster state. The platform provides
Groups multiple read requests into a single server call to reduce network overhead and improve throughput.
Acest proiect este un serviciu de embedding BERT de înaltă performanță și un server de inferență conceput pentru a mapa secvențele de text în vectori numerici de lungime fixă. Funcționează ca un microserviciu de învățare automată și server de model distribuit care decuplează gestionarea cererilor de calculul intensiv. Sistemul utilizează o infrastructură de mesagerie ZeroMQ pentru a oferi comunicare cu latență scăzută între clienții distribuiți și serverul de inferență. Încorporează procesarea în loturi pe partea de server și scalarea workload-ului GPU pentru a maximiza utilizarea hardware-ului și a gestiona volume mari de cereri. Platforma suportă infrastructura de căutare semantică prin generarea de embedding-uri cross-modale atât pentru text, cât și pentru imagini într-un spațiu vectorial partajat. Acest lucru permite căutarea cross-modală, clasarea relevanței conținutului și re-clasarea rezultatelor pe baza alinierii semantice între conținutul vizual și descrierile textuale. Serviciul poate fi implementat ca un microserviciu elastic accesibil prin protocoale gRPC, HTTP sau WebSocket, dispunând de streaming duplex non-blocant pentru gestionarea seturilor mari de date.
Groups individual requests into optimized batches to maximize GPU throughput during inference.
StreamDiffusion is an interactive generative AI framework and inference engine designed for the low-latency delivery of image and video streams. It provides a real-time Stable Diffusion pipeline for text-to-image and image-to-image generation, enabling the creation of continuous generative image streams with minimized computational delay. The framework optimizes throughput using a pre-computed cache engine and residual-based guidance approximation to reduce the number of required model passes. It further manages GPU load through similarity-based frame skipping, which avoids redundant computat
Implements batching of inference requests to maximize GPU throughput and minimize computational overhead.
FlexLLMGen is an inference engine and runtime designed to run large language models on a single GPU by combining weight compression with tensor offloading. It reduces model weight memory usage by approximately 70% through 4-bit quantization, and stores model parameters, attention cache, and hidden states across GPU, CPU, and disk to fit models larger than available GPU memory. The project distinguishes itself through a throughput-oriented batching approach that processes multiple generation requests together in large batches to maximize throughput on a single GPU. It also supports distributed
Processes multiple generation requests together in large batches to maximize throughput on a single GPU.
This project is an AI singing voice conversion system and vocal processor used for training generative voice models and converting vocal recordings or live input into a target voice. It functions as a VITS model trainer and a real-time voice changer that transforms vocal timbre and pitch to change the identity of a singer. The system provides a graphical management dashboard for controlling training hyperparameters and voice conversion presets. It supports low-latency audio streaming for live microphone input and employs pitch estimation to ensure precise matching between source and target vo
Implements grouping of multiple audio segments into single GPU execution passes to accelerate batch inference throughput.
This is a Raft consensus library and distributed consensus engine implemented in Go. It provides the primitives necessary to build fault-tolerant distributed services by implementing a replicated state machine that ensures a group of servers agree on a shared system state through leader election and log replication. The project distinguishes itself through a pluggable architecture for storage backends and snapshot storage, decoupling the consensus logic from physical persistence. It includes specialized mechanisms for leadership transfer, protocol version management to support rolling upgrade
Haftraft processes multiple committed log entries in a single operation to improve throughput and reduce system overhead.
Yoga is a GraphQL server framework and runtime-agnostic HTTP handler used to build and deploy GraphQL APIs. It functions as a toolkit for managing schemas and resolvers, providing a spec-compliant environment for hosting APIs across diverse JavaScript runtimes, including Node.js, Deno, Bun, and serverless cloud environments. The project distinguishes itself through its ability to act as an Apollo Federation gateway, composing multiple subgraphs into a single unified supergraph. It also serves as a dedicated subscription server, delivering real-time data streaming via both WebSockets and Serve
Allows combining multiple GraphQL requests into a single network call to reduce overhead and round trips.
tensorrtx is a computer vision inference engine and model implementation library designed for graphics processor acceleration. It provides a framework for optimizing deep learning models through a GPU inference optimizer, a deep learning model converter for transforming weights from frameworks like TensorFlow and PyTorch, and a custom plugin library to implement operations not natively supported by the TensorRT API. The project distinguishes itself through a comprehensive collection of pre-defined network implementations, ranging from various YOLO versions and DETR transformers for object det
Implements dynamic batching for inference workloads to optimize the balance between throughput and latency.
gspread is a Python client library and API wrapper designed for programmatically interacting with Google Sheets. It serves as a spreadsheet automation library that enables the creation, organization, and management of cloud-based spreadsheets via Python scripts. The library provides a simplified interface for Google Sheets automation, allowing users to read, write, and update data without writing raw HTTP requests. It supports cloud spreadsheet integration, enabling external Python applications to use Google Sheets as a data storage layer. The project covers a broad range of capabilities inc
Implements request batching to group multiple data updates into single network calls for improved performance.
Combines short requests into batches and splits long sequences across GPUs for balanced throughput.
Combines dynamic batching and concurrent execution to maximize hardware utilization during model serving.
KServe is a Kubernetes-native platform for deploying and serving machine learning models as scalable inference services. It supports both generative AI models, including large language models, and traditional predictive models from frameworks such as TensorFlow, PyTorch, Scikit-Learn, XGBoost, and ONNX. The platform manages the full lifecycle of model deployments, including revision tracking, canary rollouts, A/B testing, and automatic rollbacks, and provides serverless scale-to-zero capabilities for cost-efficient resource management. KServe distinguishes itself through a standardized infere
Groups multiple prediction requests into a single batch to improve throughput on GPU and CPU runtimes.
KServe is an open platform for deploying and serving generative and predictive AI models on Kubernetes. It defines inference services as custom resources with declarative YAML specifications, enabling a Kubernetes-native approach to model deployment and lifecycle management. The platform leverages Knative-based serverless scaling for automatic scale-to-zero and revision management, and supports a pluggable serving runtime architecture that maps model formats to containerized execution environments. KServe distinguishes itself through model-aware autoscaling that scales replicas based on token
Accumulates multiple prediction requests and processes them together to increase throughput.
OpenChat este un framework pentru antrenarea, fine-tuning-ul și deployment-ul modelelor lingvistice mari optimizate pentru sarcini de raționament conversațional și matematic. Oferă un ciclu de viață complet pentru aceste modele, variind de la pipeline-uri de antrenare și stack-uri de deployment până la o interfață de chat web. Proiectul se concentrează pe permiterea execuției modelelor de înaltă performanță pe hardware de consum, fără a fi nevoie de acceleratoare de nivel enterprise. Include un server de inferență gata de producție care implementează protocolul OpenAI chat completion și utilizează batching-ul dinamic al cererilor pentru a optimiza throughput-ul hardware. Sistemul acoperă întregul flux de lucru operațional, inclusiv tokenizarea seturilor de date și fine-tuning-ul modelelor prin antrenare fără padding și învățare prin consolidare (reinforcement learning). Se extinde, de asemenea, la găzduirea API-urilor cu autentificare bazată pe chei și o interfață grafică pentru interacțiunea umană în timp real.
Uses dynamic request batching to group multiple API requests into a single inference pass for higher throughput.
orpc is a contract-first API development framework for TypeScript that starts with a shared contract definition and generates type-safe clients and servers from that single source of truth. It guarantees end-to-end type safety, meaning inputs, outputs, errors, and streaming data are all checked at compile time across the client–server boundary. What distinguishes orpc from typical RPC frameworks is its ability to export contracts as OpenAPI specifications, to optimize server-side rendering by calling API handlers directly inside the server process, and to support real‑time bidirectional commu
Groups multiple API requests into a single call to reduce network overhead and improve efficiency.
fastllm is a set of specialized software components for model weight conversion, Mixture-of-Experts runtimes, and tensor parallelism. It provides an OpenAI compatible API server to expose large language model capabilities through a standardized request format. The project features a tensor parallelism framework that splits computational workloads across multiple GPUs to accelerate execution. It includes a dedicated runtime optimized for Mixture-of-Experts architectures and a quantization tool to convert model weights into lower precision formats to reduce memory usage and increase throughput.
Groups multiple incoming requests into single execution passes to maximize GPU utilization and reduce token latency.
Acest proiect este un ghid arhitectural MLOps și un framework pentru proiectarea și implementarea sistemelor de deep learning în medii de producție. Oferă o abordare structurată pentru implementarea inferenței modelelor, orchestrarea pipeline-urilor ML și crearea de arhitecturi de machine learning la nivel de producție. Proiectul se distinge printr-un accent pe deep learning distribuit și optimizarea AI la margine (edge AI). Acoperă metodologii pentru paralelizarea antrenării modelelor pe mai multe GPU-uri pentru a gestiona seturi mari de date și aplică tehnici precum cuantizarea și distilarea pentru a reduce dimensiunea modelului pentru hardware-ul embedded. Suprafața de capabilități se extinde la monitorizare și observabilitate, incluzând urmărirea performanței modelului, data drift-ul și metricile experimentelor. Abordează, de asemenea, orchestrarea fluxului de lucru al datelor, versionarea seturilor de date prin object stores și gestionarea cererilor de inferență de mare volum folosind batching adaptiv și orchestrare bazată pe containere.
Implements adaptive batching to maximize GPU throughput while maintaining latency limits for model inference.
exllamav2 este o bibliotecă de inferență de înaltă performanță concepută pentru a rula modele de limbaj mari local pe GPU-uri de consum. Oferă un runner accelerat prin GPU și instrumente de cuantizare pentru a permite execuția modelelor fără a depinde de servicii de calcul bazate pe cloud. Proiectul dispune de un utilitar de cuantizare care comprimă modelele în bitrate-uri mixte între doi și opt biți pentru a reduce cerințele de memorie video (VRAM). Se distinge printr-un generator de text batch care gestionează cererile grupate și deduplică datele din cache pentru a crește throughput-ul. Biblioteca acoperă o suprafață largă de capabilități, inclusiv streaming asincron de token-uri pentru output în timp real, execuție de kernel-uri GPU personalizate pentru operații de algebră liniară și maparea memoriei locale pentru acces cu latență scăzută la ponderile modelului.
Groups multiple model inference requests into a single hardware execution pass to maximize GPU throughput.
exllamav2 este un motor de inferență și framework de înaltă performanță pentru executarea modelelor de limbaj mari local pe GPU-uri de clasă consumer. Oferă un sistem complet pentru deployment-ul local al modelelor, incluzând un motor de inferență specializat și instrumente pentru cuantizarea modelelor. Proiectul dispune de un framework de inferență multi-GPU care distribuie sarcinile de lucru pe mai multe plăci grafice pentru a rula modele care depășesc capacitatea de memorie a unui singur dispozitiv. Include un cuantizator de modele GPU capabil să convertească modelele în formate de precizie mixtă între 2 și 8 biți pentru a echilibra utilizarea memoriei și acuratețea. Motorul suportă generarea de text cu throughput ridicat prin inferență paralelă bazată pe batch-uri și streaming asincron de output. Aceste capabilități sunt susținute de kernel-uri CUDA personalizate și deduplicarea cache-ului pentru a optimiza utilizarea hardware-ului și a reduce latența în timpul generării de token-uri.
Executes multiple text completion prompts simultaneously using batch-based parallel inference to maximize GPU utilization.