REST-API-Server für ML-Modelle

BentoML is a machine learning model serving framework and GPU-accelerated inference server designed to package, deploy, and scale AI models as production-ready REST APIs. It functions as an AI model lifecycle manager and an inference graph orchestrator, enabling the chaining of multiple models and custom logic into complex pipelines for advanced task sequences. The framework distinguishes itself through a dynamic batching engine that optimizes GPU throughput and an artifact-based packaging system that bundles model weights and dependencies into immutable archives for consistent deployment. It

Triton Inference Server is a high-performance server designed to deploy machine learning models from multiple frameworks across GPUs and CPUs. It functions as a hardware-accelerated inference engine and a gRPC inference gateway, providing a standardized communication layer for transmitting binary tensor data with low latency. The system acts as a multi-framework model orchestrator, allowing users to link multiple AI models into ensembles and scripts to create complex inference pipelines. It also serves as a model lifecycle manager, providing controls to load, unload, and monitor the performan

Lorax is a GPU-accelerated inference server and multi-adapter engine designed for serving large language models. It functions as a high-throughput system capable of deploying models via Kubernetes and managing the dynamic swapping of Low-Rank Adaptation adapters per request. The server distinguishes itself through multi-adapter dynamic batching, which allows requests using different adapter weights to be processed in a single GPU forward pass. It employs just-in-time adapter loading and weighted adapter merging to maximize throughput and enable multi-tasking without sacrificing performance.

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

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

llm-d is a distributed serving framework designed for large language model inference. It functions as an inference orchestrator and gateway, providing a control plane for deploying model replicas and managing hardware accelerators. The system includes a batch inference scheduler and a cache manager to coordinate request flow and memory utilization. The project is distinguished by a disaggregated serving architecture that separates prefill and decode execution phases across specialized workers to maximize throughput. It employs a hardware-agnostic control plane and tiered cache offloading, mov

TensorFlow Serving is a high-performance machine learning inference server designed to deploy TensorFlow models to production environments. It functions as a complete serving system that executes predictions on input data through a graph executor, providing network endpoints that eliminate the need for a separate runtime environment for client applications. The system is distinguished by its model version manager, which organizes and selects specific model versions within a directory hierarchy. It uses a filesystem watcher to detect new model versions and trigger automatic updates without int

OpenVINO is an AI inference engine and model serving platform designed to execute optimized deep learning models across CPUs, GPUs, and NPUs through a unified API. It includes a model optimization toolkit for converting, quantizing, and compressing models from various frameworks, alongside a specialized generative AI runtime for large language models. The project distinguishes itself through a plugin-based hardware acceleration layer that maps neural network operations to vendor-specific drivers. It features advanced execution mechanisms such as continuous batching, speculative decoding, and

Triton Inference Server is a high-performance AI model inference server and multi-framework model runtime designed for deploying machine learning models across cloud, data center, and embedded edge infrastructure. It serves as an execution engine that allows for the concurrent running of models from various frameworks to optimize hardware utilization. The project features a dynamic batching inference engine that groups individual requests into larger batches to increase total processing throughput. It also provides a model ensemble pipeline, which enables the chaining of multiple models toget

Seldon Core is a Kubernetes-based machine learning model server and MLOps inference framework. It functions as a multi-model serving engine and pipeline orchestrator, packaging models as scalable microservices that are exposed via standardized REST and gRPC APIs. The project distinguishes itself through graph-based inference pipelines that chain models and data transformers into sequential workflows. It optimizes hardware utilization via multi-model shared serving and dynamic memory overcommit strategies, while supporting production experimentation through weighted traffic routing, A/B testin

LightLLM is a high-performance serving framework for deploying and executing large language models. It functions as a multi-GPU inference engine and server capable of handling dense architectures, mixture-of-experts designs, and multimodal models that process both text and images. The system is distinguished by its specialized support for Mixture-of-Experts models using expert parallelism and fused kernels. It implements structured text generation through deterministic state machines and pushdown automata to enforce precise output formats. To optimize throughput, the framework employs specula

vLLM is a high-throughput inference engine designed for the efficient serving and execution of large language models. It functions as a production-ready distributed model server, providing standard API protocols for online serving while also supporting offline batch processing. The system is built to maximize token generation speed and memory efficiency, enabling both large-scale cloud deployments and local execution on personal hardware. The project distinguishes itself through advanced memory management and request scheduling techniques, most notably its use of non-contiguous key-value cach

Text Generation Inference is a production-ready engine designed for the deployment and serving of large language models. It functions as a containerized runtime environment that manages model execution, scales across distributed hardware, and provides high-performance inference capabilities for demanding production environments. The project distinguishes itself through advanced optimization techniques, including continuous batching to maximize hardware utilization and tensor parallelism to shard large models across multiple accelerator cards. It supports efficient inference through custom com

gpustack is a GPU cluster management platform and LLM inference orchestrator. It functions as a centralized system for pooling and orchestrating graphics processing units across local servers and cloud environments, serving as a heterogeneous compute manager for diverse hardware and software configurations. The system provides a secure AI model deployment gateway that serves models as scalable services using key-based authentication. It includes a GPU resource scheduler that balances workloads across accelerators and coordinates multiple inference engines to map specific AI models to compatib

LocalAI is a self-hosted inference server that enables the execution of machine learning models directly on local hardware. By providing a unified interface for text, image, and audio processing, it allows users to maintain full control over data privacy and infrastructure costs while eliminating dependencies on external network services. The platform functions as an API gateway that mimics standard cloud-based artificial intelligence interfaces, allowing existing applications to integrate local models as drop-in replacements. It utilizes a container-based architecture to package runtimes and

OpenLLM is a framework for deploying, managing, and scaling open-source large language models

Exo is a distributed inference engine designed to run machine learning models across local hardware. It functions as a network orchestration layer that automatically discovers available devices to form a unified computing cluster, allowing users to scale artificial intelligence workloads by distributing computational tasks across multiple machines. The platform distinguishes itself through its ability to manage the entire lifecycle of local models while providing a standardized gateway for external applications. By translating local model outputs into industry-standard formats, it enables exi

Serving is a high-performance framework designed for deploying and scaling machine learning models as production services. It functions as a distributed inference engine that enables the execution of complex data processing workflows by chaining multiple models into directed acyclic graphs. The platform distinguishes itself through its ability to manage the entire production model lifecycle, allowing for hot-swappable versioning that updates services without downtime. It supports horizontal scaling through distributed model sharding and optimizes high-dimensional data retrieval via specialize