Update README.md

README.md

@@ -42,4 +42,37 @@ generation_output = model.generate(
     streamer=streamer,
     max_new_tokens=512
 )
+```
+
+### vLLM
+
+Support is added to vLLM:
+
+```
+pip install git+https://github.com/mistralai/vllm-release@add-mistral
+```
+
+Run using this model:
+
+```python
+from vllm import LLM, SamplingParams
+
+prompts = [
+    "Hello, my name is",
+    "The president of the United States is",
+    "The capital of France is",
+    "The future of AI is",
+]
+sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
+
+llm = LLM(model="casperhansen/mistral-7b-instruct-v0.1-awq", quantization="awq", dtype="half")
+
+outputs = llm.generate(prompts, sampling_params)
+
+# Print the outputs.
+for output in outputs:
+    prompt = output.prompt
+    generated_text = output.outputs[0].text
+    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+
 ```