update pd example yaml

Signed-off-by: YuhanLiu11 <yliu738@wisc.edu>

Author: YuhanLiu11

examples/disaggregated_prefill/pd.yaml

@@ -5,7 +5,7 @@ servingEngineSpec:
   containerPort: 8000
   modelSpec:
     # Prefill node configuration
-    - name: "mistral-prefill"
+    - name: "llama-prefill"
       repository: "lmcache/vllm-openai"
       tag: "2025-05-17-v1"
       modelURL: "meta-llama/Llama-3.1-8B-Instruct"
@@ -26,18 +26,18 @@ servingEngineSpec:
         kvRole: "kv_producer"
         enableNixl: true
         nixlRole: "sender"
-        nixlPeerHost: "pd-mistral-decode-engine-service"
+        nixlPeerHost: "vllm-llama-decode-engine-service"
         nixlPeerPort: "55555"
         nixlBufferSize: "1073741824"  # 1GB
         nixlBufferDevice: "cuda"
         nixlEnableGc: true
         enablePD: true
         cpuOffloadingBufferSize: 0
-      hf_token: <your-hf-token>
+      hf_token: "<HF_TOKEN>"
       labels:
-        model: "mistral-prefill"
+        model: "llama-prefill"
     # Decode node configuration
-    - name: "mistral-decode"
+    - name: "llama-decode"
       repository: "lmcache/vllm-openai"
       tag: "2025-05-17-v1"
       modelURL: "meta-llama/Llama-3.1-8B-Instruct"
@@ -63,13 +63,13 @@ servingEngineSpec:
         nixlBufferDevice: "cuda"
         nixlEnableGc: true
         enablePD: true
-      hf_token: <your-hf-token>
+      hf_token: "<HF_TOKEN>"
       labels:
-        model: "mistral-decode"
+        model: "llama-decode"
 routerSpec:
   enableRouter: true
   repository: "lmcache/lmstack-router"
-  tag: "pd-new"
+  tag: "pd-05-26"
   replicaCount: 1
   containerPort: 8000
   servicePort: 80
@@ -89,23 +89,6 @@ routerSpec:
     release: "router"
   extraArgs:
     - "--prefill-model-labels"
-    - "mistral-prefill"
+    - "llama-prefill"
     - "--decode-model-labels"
-    - "mistral-decode"
-# cacheserverSpec:
-#   replicaCount: 1
-#   containerPort: 8080
-#   servicePort: 81
-#   serde: "naive"
-#   repository: "lmcache/vllm-openai"
-#   tag: "2025-05-08-v1"
-#   resources:
-#     requests:
-#       cpu: "2"
-#       memory: "8G"
-#     limits:
-#       cpu: "2"
-#       memory: "10G"
-#   labels:
-#     environment: "cacheserver"
-#     release: "cacheserver"
+    - "llama-decode"