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
msoedov/langcorn
LangCorn is an API server designed to streamline the deployment and serving of LangChain-based LLM applications and agents. It leverages the FastAPI framework to provide a high-performance, scalable, and robust solution for handling language processing requests. Key features include easy deployment of LangChain models and pipelines, enabling users to quickly expose their LLM creations as RESTful APIs. It supports custom pipelines and processing, offering flexibility for various AI applications. The server integrates authentication functionality, allowing for secure API access. LangCorn also provides mechanisms for handling conversational memory and allows for overriding default LLM parameters per request, such as temperature, max tokens, and model name. This makes it suitable for developing and operating LLM-powered applications in production environments, bridging the gap between LangChain development and scalable API deployment. The project emphasizes its role in LLMops by simplifying the serving aspect of LLM ecosystems.
https://github.com/msoedov/langcorn
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...