diff --git a/helm/dashboards/vllm-dashboard.json b/helm/dashboards/vllm-dashboard.json
index 753a9be11..e75a7f2a1 100644
--- a/helm/dashboards/vllm-dashboard.json
+++ b/helm/dashboards/vllm-dashboard.json
@@ -369,7 +369,7 @@
       "targets": [
         {
           "editorMode": "builder",
-          "expr": "avg(vllm:time_per_output_token_seconds_sum) / avg(vllm:time_per_output_token_seconds_count)",
+          "expr": "avg(vllm:request_time_per_output_token_seconds_sum) / avg(vllm:request_time_per_output_token_seconds_count)",
           "legendFormat": "Avg ITL",
           "range": true,
           "refId": "A"
@@ -656,6 +656,7 @@
           "color": {
             "mode": "palette-classic"
           },
+          "unit": "percentunit",
           "custom": {
             "axisBorderShow": false,
             "axisCenteredZero": false,
@@ -729,7 +730,7 @@
       "targets": [
         {
           "editorMode": "builder",
-          "expr": "vllm:gpu_cache_usage_perc",
+          "expr": "vllm:kv_cache_usage_perc",
           "legendFormat": "{{instance}}",
           "range": true,
           "refId": "A"
@@ -834,70 +835,6 @@
       "title": "GPU KV Cache Hit Rate",
       "type": "timeseries"
     },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "prometheus"
-      },
-      "description": "Requests moved from GPU to CPU",
-      "fieldConfig": {
-        "defaults": {
-          "color": {
-            "mode": "thresholds"
-          },
-          "mappings": [],
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green"
-              },
-              {
-                "color": "red",
-                "value": 0
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 8,
-        "w": 12,
-        "x": 12,
-        "y": 39
-      },
-      "id": 21,
-      "options": {
-        "colorMode": "value",
-        "graphMode": "area",
-        "justifyMode": "auto",
-        "orientation": "auto",
-        "percentChangeColorMode": "standard",
-        "reduceOptions": {
-          "calcs": [
-            "lastNotNull"
-          ],
-          "fields": "",
-          "values": false
-        },
-        "showPercentChange": false,
-        "textMode": "auto",
-        "wideLayout": true
-      },
-      "pluginVersion": "12.0.0+security-01",
-      "targets": [
-        {
-          "editorMode": "builder",
-          "expr": "vllm:num_requests_swapped",
-          "legendFormat": "Swapped Requests",
-          "range": true,
-          "refId": "A"
-        }
-      ],
-      "title": "Number of Swapped Requests",
-      "type": "stat"
-    },
     {
       "collapsed": false,
       "gridPos": {
@@ -921,6 +858,7 @@
           "color": {
             "mode": "palette-classic"
           },
+          "unit": "percentunit",
           "custom": {
             "axisBorderShow": false,
             "axisCenteredZero": false,
@@ -995,7 +933,7 @@
         {
           "disableTextWrap": false,
           "editorMode": "builder",
-          "expr": "vllm:gpu_cache_usage_perc",
+          "expr": "vllm:kv_cache_usage_perc",
           "fullMetaSearch": false,
           "includeNullMetadata": true,
           "legendFormat": "GPU Usage",
diff --git a/helm/dashboards/vllm-model-metrics-dashboard.json b/helm/dashboards/vllm-model-metrics-dashboard.json
index e3e579391..c2b9df991 100644
--- a/helm/dashboards/vllm-model-metrics-dashboard.json
+++ b/helm/dashboards/vllm-model-metrics-dashboard.json
@@ -402,7 +402,7 @@
             },
             "disableTextWrap": false,
             "editorMode": "builder",
-            "expr": "histogram_quantile(0.99, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
+            "expr": "histogram_quantile(0.99, sum by(le) (rate(vllm:request_time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
             "fullMetaSearch": false,
             "includeNullMetadata": false,
             "instant": false,
@@ -418,7 +418,7 @@
             },
             "disableTextWrap": false,
             "editorMode": "builder",
-            "expr": "histogram_quantile(0.95, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
+            "expr": "histogram_quantile(0.95, sum by(le) (rate(vllm:request_time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
             "fullMetaSearch": false,
             "hide": false,
             "includeNullMetadata": false,
@@ -435,7 +435,7 @@
             },
             "disableTextWrap": false,
             "editorMode": "builder",
-            "expr": "histogram_quantile(0.9, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
+            "expr": "histogram_quantile(0.9, sum by(le) (rate(vllm:request_time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
             "fullMetaSearch": false,
             "hide": false,
             "includeNullMetadata": false,
@@ -452,7 +452,7 @@
             },
             "disableTextWrap": false,
             "editorMode": "builder",
-            "expr": "histogram_quantile(0.5, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
+            "expr": "histogram_quantile(0.5, sum by(le) (rate(vllm:request_time_per_output_token_seconds_bucket{model_name=\"$model_name\"}[$__rate_interval])))",
             "fullMetaSearch": false,
             "hide": false,
             "includeNullMetadata": false,
@@ -468,7 +468,7 @@
               "uid": "${DS_PROMETHEUS}"
             },
             "editorMode": "code",
-            "expr": "rate(vllm:time_per_output_token_seconds_sum{model_name=\"$model_name\"}[$__rate_interval])\n/\nrate(vllm:time_per_output_token_seconds_count{model_name=\"$model_name\"}[$__rate_interval])",
+            "expr": "rate(vllm:request_time_per_output_token_seconds_sum{model_name=\"$model_name\"}[$__rate_interval])\n/\nrate(vllm:request_time_per_output_token_seconds_count{model_name=\"$model_name\"}[$__rate_interval])",
             "hide": false,
             "instant": false,
             "legendFormat": "Mean",
@@ -484,7 +484,7 @@
           "type": "prometheus",
           "uid": "${DS_PROMETHEUS}"
         },
-        "description": "Number of requests in RUNNING, WAITING, and SWAPPED state",
+        "description": "Number of requests in RUNNING, and WAITING",
         "fieldConfig": {
           "defaults": {
             "color": {
@@ -577,23 +577,6 @@
             "refId": "A",
             "useBackend": false
           },
-          {
-            "datasource": {
-              "type": "prometheus",
-              "uid": "${DS_PROMETHEUS}"
-            },
-            "disableTextWrap": false,
-            "editorMode": "builder",
-            "expr": "vllm:num_requests_swapped{model_name=\"$model_name\"}",
-            "fullMetaSearch": false,
-            "hide": false,
-            "includeNullMetadata": true,
-            "instant": false,
-            "legendFormat": "Num Swapped",
-            "range": true,
-            "refId": "B",
-            "useBackend": false
-          },
           {
             "datasource": {
               "type": "prometheus",
@@ -608,7 +591,7 @@
             "instant": false,
             "legendFormat": "Num Waiting",
             "range": true,
-            "refId": "C",
+            "refId": "B",
             "useBackend": false
           }
         ],
@@ -869,24 +852,11 @@
               "uid": "${DS_PROMETHEUS}"
             },
             "editorMode": "code",
-            "expr": "vllm:gpu_cache_usage_perc{model_name=\"$model_name\"}",
+            "expr": "vllm:kv_cache_usage_perc{model_name=\"$model_name\"}",
             "instant": false,
             "legendFormat": "GPU Cache Usage",
             "range": true,
             "refId": "A"
-          },
-          {
-            "datasource": {
-              "type": "prometheus",
-              "uid": "${DS_PROMETHEUS}"
-            },
-            "editorMode": "code",
-            "expr": "vllm:cpu_cache_usage_perc{model_name=\"$model_name\"}",
-            "hide": false,
-            "instant": false,
-            "legendFormat": "CPU Cache Usage",
-            "range": true,
-            "refId": "B"
           }
         ],
         "title": "Cache Utilization",