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
ajndkr/lanarky
Lanarky is a web framework engineered in Python (3.9+) exclusively for developers constructing microservices powered by Large Language Models (LLMs). It leverages the robust foundation of FastAPI, providing familiar features to FastAPI users while catering to the unique requirements of LLM application development. A core design principle is its "LLM-first" approach, ensuring it's tailored for LLM use cases without imposing vendor lock-in to specific LLM tooling or cloud providers. A key feature of Lanarky is its built-in support for streaming over both HTTP and WebSockets, which is crucial for real-time interactive LLM applications like chatbots, allowing for efficient communication and progressive rendering of AI responses. Although the project is in maintenance mode, indicating that active feature development has ceased, it addresses critical bugs and security issues. Lanarky simplifies the process of building LLM microservices, offering a powerful abstraction layer to define endpoints that interact with LLMs, as demonstrated by examples using OpenAI's ChatCompletion service.
https://github.com/ajndkr/lanarky
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...