diff --git a/README.md b/README.md
index 1764e197..f1a2bd16 100644
--- a/README.md
+++ b/README.md
@@ -21,7 +21,7 @@ workloads currently.
 [Kubernetes]:https://kubernetes.io
 [Architecture Documentation]:docs/architecture.md
 [Gateway API Inference Extension (GIE)]:https://github.com/kubernetes-sigs/gateway-api-inference-extension
-[P/D Disaggregation]:docs/dp.md
+[P/D Disaggregation]:docs/pd_disagg.md
 [Gateway API]:https://github.com/kubernetes-sigs/gateway-api
 [Envoy]:https://github.com/envoyproxy/envoy
 [ext-proc]:https://www.envoyproxy.io/docs/envoy/latest/configuration/http/http_filters/ext_proc_filter
diff --git a/docs/architecture.md b/docs/architecture.md
index 2b981151..8b54fd5c 100644
--- a/docs/architecture.md
+++ b/docs/architecture.md
@@ -302,7 +302,7 @@ The **vLLM sidecar** handles orchestration between Prefill and Decode stages. It
 - Local memory management
 - Experimental protocol compatibility
 
-> **Note**: The detailed P/D design is available in this document: [Disaggregated Prefill/Decode in llm-d](./dp.md)
+> **Note**: The detailed P/D design is available in this document: [Disaggregated Prefill/Decode in llm-d](./pd_disagg.md)
 ---
 
 ## InferencePool & InferenceModel Design
diff --git a/docs/dp.md b/docs/pd_disagg.md
similarity index 100%
rename from docs/dp.md
rename to docs/pd_disagg.md