#vllm

vllm-project/semantic-router

Go

89

health

System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge

mostlygeek/llama-swap

Go

88

health

Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc

vllm-project/vllm-ascend

C++

82

health

Community maintained hardware plugin for vLLM on Ascend

lightseekorg/smg

Rust

79

health

Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across SGLang, vLLM, TRT-LLM, OpenAI, Gemini & more. Industry-first gRPC pipeline, KV cache-aware routing, chat history, tokenization caching, Responses API, embeddings, WASM plugins, MCP, and multi-tenant auth.