Engine-agnostic, high-performance model-routing gateway for large-scale LLM deployments. Centralizes worker lifecycle management, balances traffic across HTTP/gRPC/OpenAI-compatible backends, and provides enterprise-ready control over history storage, MCP tooling, and privacy-sensitive workflows.
🚀 Maximize GPU Utilization | Cache-aware routing understands your inference engine's KV cache state—whether vLLM, TensorRT-LLM, TokenSpeed, or SGLang—to reuse prefixes and reduce redundant computation. | 🔌 One API, Any Backend | Route to self-hosted models (vLLM, TensorRT-LLM, TokenSpeed, SGLang) or cloud providers (OpenAI, Anthropic, Gemini, Bedrock, and more) through a single unified endpoint. | ⚡ Built for Speed | Native Rust with gRPC pipelines, sub-millisecond routing decisions, and zero-copy tokenization. Circuit breakers and automatic failover keep things running. | 🔒 Enterprise Control | Multi-tenant rate limiting with OIDC, WebAssembly plugins for custom logic, and a privacy boundary that keeps conversation history within your infrastructure. | 📊 Full Observability | 40+ Prometheus metrics, OpenTelemetry tracing, and structured JSON logs with request correlation—know exactly what's happening at every layer. |
API Coverage: OpenAI Chat/Completions/Embeddings, Responses API for agents, Anthropic Messages, and MCP tool execution.
Install — pick your preferred method:
docker pull lightseekorg/smg:latest
pip install smg
cargo install smg
Run — point SMG at your inference workers:
smg launch --worker-urls http://localhost:8000
smg launch --worker-urls http://gpu1:8000 http://gpu2:8000 --policy cache_aware
smg launch --worker-urls http://gpu1:8000 --enable-mesh \
--mesh-advertise-host 10.0.0.1 --mesh-peer-urls 10.0.0.2:39527
Use — send requests to the gateway:
curl http://localhost:30000/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{"model": "llama3", "messages": [{"role": "user", "content": "Hello!"}]}'
That's it. SMG is now load-balancing requests across your workers.
| Self-Hosted | Cloud Providers |
|---|---|
| vLLM | OpenAI |
| TensorRT-LLM | Anthropic |
| TokenSpeed | Google Gemini |
| SGLang | AWS Bedrock |
| Ollama | Azure OpenAI |
| Any OpenAI-compatible server | Any OpenAI-compatible provider |
| Feature | Description |
|---|---|
| cache_aware, round_robin, power_of_two, consistent_hashing, prefix_hash, manual, random, bucket | |
| Native gRPC with streaming, reasoning extraction, and tool call parsing | |
| Connect external tool servers via Model Context Protocol | |
| Mesh networking with SWIM protocol for multi-node deployments | |
| Pluggable storage: PostgreSQL, Oracle, Redis, or in-memory | |
| Extend with custom WebAssembly logic | |
| Circuit breakers, retries with backoff, rate limiting |
|
ArchitectureConfigurationAPI ReferenceKubernetes SetupWe welcome contributions! See Contributing Guide for details.