Update README.md

README.md

@@ -146,6 +146,19 @@ generated_tokens = outputs[0, inputs.input_ids.shape[1]:]
 print(tokenizer.decode(generated_tokens, skip_special_tokens=True))
 ```
 
+## vLLM Integration:
+
+You can also run the model in vLLM, using the above branch install:
+
+```vllm serve --model_impl transformers --enforce-eager nanochat-students/nanochat-d20```
+
+And then you can call the model like so:
+
+```sh
+url http://localhost:8000/v1/completions \
+>   -H "Content-Type: application/json" \
+>   -d '{"model": "nanochat-students/nanochat-d20", "prompt": "What is the capital of France?, "max_tokens": 7, "temperature": 0}'
+```
 
 ## Chat SFT Training Metrics