Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main

examples/ray/README.md

@@ -0,0 +1,19 @@
+This is an example of doing LLM inference with [Ray](https://docs.ray.io/en/latest/index.html) and [Ray Serve](https://docs.ray.io/en/latest/serve/index.html).
+
+First, install the requirements:
+
+```bash
+$ pip install -r requirements.txt
+```
+
+Deploy a GGUF model to Ray Serve with the following command:
+
+```bash
+$ serve run llm:llm_builder model_path='../models/mistral-7b-instruct-v0.2.Q4_K_M.gguf'
+```
+
+This will start an API endpoint at `http://localhost:8000/`. You can query the model like this:
+
+```bash
+$ curl -k -d '{"prompt": "tell me a joke", "max_tokens": 128}' -X POST http://localhost:8000
+```

examples/ray/llm.py

@@ -0,0 +1,20 @@
+from starlette.requests import Request
+from typing import Dict
+from ray import serve
+from ray.serve import Application
+from llama_cpp import Llama
+
+@serve.deployment
+class LlamaDeployment:
+    def __init__(self, model_path: str):
+        self._llm = Llama(model_path=model_path)
+
+    async def __call__(self, http_request: Request) -> Dict:
+        input_json = await http_request.json()
+        prompt = input_json["prompt"]
+        max_tokens = input_json.get("max_tokens", 64)
+        return self._llm(prompt, max_tokens=max_tokens)
+
+
+def llm_builder(args: Dict[str, str]) -> Application:
+    return LlamaDeployment.bind(args["model_path"])

examples/ray/requirements.txt

@@ -0,0 +1,3 @@
+ray[serve]
+--extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
+llama-cpp-python