diff --git a/README.md b/README.md
index 87d8156e..f4eb27ee 100644
--- a/README.md
+++ b/README.md
@@ -39,7 +39,7 @@ You can learn more about Triton backends in the [backend
 repo](https://github.com/triton-inference-server/backend).
 
 
-This is a [Python-based backend](https://github.com/triton-inference-server/backend/blob/main/docs/python_based_backends.md#python-based-backends). 
+This is a [Python-based backend](https://github.com/triton-inference-server/backend/blob/main/docs/python_based_backends.md#python-based-backends).
 When using this backend, all requests are placed on the
 vLLM AsyncEngine as soon as they are received. Inflight batching and paged attention is handled
 by the vLLM engine.