litserve 0.1.4

Lightweight AI server.

LitServe: Deploy AI models Lightning fast ⚡

 

High-throughput serving engine for AI models.
Friendly interface. Enterprise scale.

---

LitServe is a FastAPI-based engine for scalable AI model deployment. Features like batching, streaming, and GPU autoscaling eliminate the need to rebuild a FastAPI server for each model.

✅ Batching       ✅ Streaming          ✅ Auto-GPU, multi-GPU   
✅ Multi-modal    ✅ PyTorch/JAX/TF     ✅ Full control          
✅ Auth           ✅ Built on Fast API  ✅ Custom specs (Open AI)

Quick start • Lightning AI • Examples • Deploy • Features • Benchmarks • Docs

 

 

Performance

LitServe (built on FastAPI), is optimized for AI workloads like model serving, embeddings, and LLM serving.

These benchmarks are for image and text classification as examples. Reproduce the full benchmarks here.

💡 Note on LLM serving: For high-performance LLM serving (like Ollama/VLLM), use LitGPT or build your custom VLLM-like server with LitServe. Optimizations like kv-caching, which can be done with LitServe, are needed to maximize LLM performance.

 

Featured examples

Key features ✅ Serve all models: LLMs, vision, etc ✅ All ML frameworks: PyTorch/Jax/sklearn/... ✅ Developer friendly: focus on AI, not infra ✅ Minimal interface: no abstractions ✅ Enterprise scale: scale huge models ✅ Auto GPU scaling: zero code changes ✅ Self host: or run on Studios

Featured examples Toy model: Hello world LLMs: Llama 3 (8B), LLM Proxy server NLP models: Any Hugging face model, BERT model Multimodal: OpenAI Clip Audio: OpenAI Whisper, AudioCraft, Stable Audio Vision: Stable diffusion 2 Speech: Text-speech (XTTS V2)

 

Quick start

Install LitServe via pip (or advanced installs):

pip install litserve

Define a server

Here's a hello world example (explore real examples):

# server.py
import litserve as ls

# STEP 1: DEFINE A MODEL API
class SimpleLitAPI(ls.LitAPI):
    # Called once at startup. Setup models, DB connections, etc...
    def setup(self, device):
        self.model = lambda x: x**2  

    # Convert the request payload to model input.
    def decode_request(self, request):
        return request["input"] 

    # Run inference on the the model, return the output.
    def predict(self, x):
        return self.model(x) 

    # Convert the model output to a response payload.
    def encode_response(self, output):
        return {"output": output} 

# STEP 2: START THE SERVER
if __name__ == "__main__":
    api = SimpleLitAPI()
    server = ls.LitServer(api, accelerator="auto")
    server.run(port=8000)

Now run the server via the command-line

python server.py

LitAPI class gives full control and hackability.
LitServer handles optimizations like batching, auto-GPU scaling, etc...

Query the server

Use the automatically generated LitServe client or write your own:

Option A - Use generated client: python client.py

Option B - Custom client example: import requests response = requests.post( "http://127.0.0.1:8000/predict", json={"input": 4.0} )

 

Deployment options

LitServe is developed by Lightning AI which provides infrastructure for deploying AI models. Self-manage deployments or use Lightning Studios for production-grade deployments without cloud headaches, security and 99.95% uptime SLA.

 

 

Feature	Self Managed	Fully Managed on Studios
Deployment	✅ Do it yourself deployment	✅ One-button cloud deploy
Load balancing	❌	✅
Autoscaling	❌	✅
Multi-machine inference	❌	✅
Authentication	❌	✅
Own VPC	❌	✅
AWS, GCP	❌	✅
Use your own cloud commits	❌	✅

 

Features

LitServe supports multiple advanced state-of-the-art features.

✅ All model types: LLMs, vision, time series, etc....
✅ Auto-GPU scaling.
✅ Authentication.
✅ Autoscaling.
✅ Batching.
✅ Streaming.
✅ All ML frameworks: PyTorch, Jax, Tensorflow, Hugging Face....
✅ Open AI spec.
10+ features....

Note: Our goal is not to jump on every hype train, but instead support features that scale under the most demanding enterprise deployments.

 

Community

LitServe is a community project accepting contributions - Let's make the world's most advanced AI inference engine.

💬 Get help on Discord
📋 License: Apache 2.0