vllm-project/vllm
vLLM is a high-throughput and memory-efficient serving and inference engine for large language models, featuring PagedAttention, continuous batching, and extensive hardware and model support.
Awesome Infra for AI › Model Serving Frameworks
BMW-InnovationLab/BMW-YOLOv4-Inference-API-GPU
This project provides a robust, GPU-accelerated REST API designed for serving object detection models based on YOLOv3 and YOLOv4 Darknet frameworks. It enables users to deploy trained models for real-time inference, offering capabilities such as loading multiple models simultaneously, performing detection on images, and retrieving bounding box predictions. The API is built for Linux environments and leverages NVIDIA GPUs for optimized performance, with support for Docker and Docker Swarm for deployment, enabling redundancy and scalability. Users can configure inference parameters like detection and NMS thresholds. It exposes various endpoints for model management (loading, listing), inference execution (single image or batch), and retrieving model-specific information (labels, configuration). The project emphasizes a 'no-code' approach to deploying these inference services, making it accessible for integrating pre-trained YOLO models into applications.
https://github.com/BMW-InnovationLab/BMW-YOLOv4-Inference-API-GPU
Also in Model Serving Frameworks
jundot/omlx
oMLX is an LLM inference server optimized for Apple Silicon, offering continuous batching, tiered KV caching, and a macOS menu bar interface for managing models locally.
jina-ai/serve
A framework for building and deploying cloud-native AI services, with native support for ML frameworks, high-performance serving, LLM streaming, and Kubernetes/Docker Compose deployment.
bentoml/OpenLLM
OpenLLM allows developers to self-host and run any open-source or custom LLMs as OpenAI-compatible API endpoints in the cloud, streamlining deployment and serving.
bentoml/BentoML
BentoML is an open-source framework for building, shipping, and scaling AI applications, providing tools to serve AI/ML models as production-ready API endpoints.
vllm-project/vllm-omni
vLLM-Omni is an extension of vLLM designed for efficient serving and inference of omni-modality AI models, encompassing text, image, video, and audio data processing.
kserve/kserve
KServe is a standardized, distributed platform for serving generative and predictive AI models on Kubernetes, providing scalable deployment and management.
Michael-A-Kuykendall/shimmy
Shimmy is a pure-Rust WebGPU inference engine providing OpenAI-compatible endpoints for local GGUF models, featuring Airframe engine and TurboShimmy INT4 KV cache compression for efficient GPU util...