fix e2e tests

Signed-off-by: Maya Barnea <mayab@il.ibm.com>

Author: mayabar

docs/architecture.md

@@ -208,27 +208,37 @@ Selects the profiles to use when running with disaggregated prefill/decode
 - **Parameters**:
   - `decodeProfile`: specifies the name of the profile used for the decode scheduling. Only needed if the decode profile is not named `decode`.
   - `prefillProfile`: specifies the name of the profile used for the prefill scheduling. Only needed if the prefill profile is not named `prefill`.
-  - `decider`: specifies the name of the decider, which determines whether disaggregated PD should be executed
-    - `name`: decider name, currently supported values are: "prefix-based-disaggregation-decider" and "always-disaggregated-decider"
-    - `parameters`: parameters for this specific decider type
+  - `deciderPluginName`: specifies the name of the decider plugin. Decider determines whether disaggregated PD should be executed
   - `primaryPort`: the base port number used for data parallel communication.
 
 **Note:** When using this plugin you must also have a PrefixCachePlugin configured in the prefill and decode scheduling profiles.
 
-**Parameters for `prefix-based-disaggregation-decider`**
+---
+
+#### Prefix Based Decider Plugin
+
+Type: `prefix-based-pd-decider`
+
+**Parameters**
 - `nonCachedTokens`: length, in token, of the uncached part of the user input above which disaggregated PD is triggered.
-- `pluginName`: the prefix plugin name. Optional, required when overriding the default plugin name.
+
+Note: `prepareDataPlugins` feature gate should be enabled
 
 **Example**
 ```yaml
+kind: EndpointPickerConfig
+featureGates:
+- prepareDataPlugins
+plugins:
+- type: prefix-based-pd-decider
+  parameters:
+    nonCachedTokens: 4
 - type: pd-profile-handler
   parameters:
     primaryPort: 8000
-    decider: 
-      name: prefix-based-disaggregation-decider
-      parameters:
-        nonCachedTokens: 10 
+    deciderPluginName: prefix-based-pd-decider
 ```
+
 ---
 
 #### ByLabelSelector

docs/disagg_pd.md

@@ -155,6 +155,8 @@ Below is a minimal `EndpointPickerConfig` that enables integration with workload
 ```yaml
 apiVersion: inference.networking.x-k8s.io/v1alpha1
 kind: EndpointPickerConfig
+featureGates:
+- prepareDataPlugins
 plugins:
   # Prefill selection: match Pods with label role=prefill
   - type: by-label
@@ -176,10 +178,12 @@ plugins:
       lruCapacityPerServer: 31250
   - type: max-score-picker
   - type: prefill-header-handler
-  - type: pd-profile-handler
+  - type: prefix-based-pd-decider
     parameters:
-      threshold: 0
-      hashBlockSize: 5
+      nonCachedTokens: 8
+  - type: pd-profile-handler
+    parameters:    
+      deciderPluginName: prefix-based-pd-decider
       primaryPort: 8000
 schedulingProfiles:
   - name: prefill

…ugins/profile/prexif_based_pd_decider.go …ugins/profile/prefix_based_pd_decider.gopkg/plugins/profile/prexif_based_pd_decider.go renamed to pkg/plugins/profile/prefix_based_pd_decider.go pkg/plugins/profile/prexif_based_pd_decider.go renamed to pkg/plugins/profile/prefix_based_pd_decider.go

@@ -126,8 +126,8 @@ var _ = ginkgo.Describe("Run end to end tests", ginkgo.Ordered, func() {
 			labelFilter2 := fmt.Sprintf(`decision_type="decode-only",model_name="%s"`, modelName)
 			decodeOnlyCount := getCounterMetric(metricsURL, "llm_d_inference_scheduler_pd_decision_total", labelFilter2)
 
-			gomega.Expect(prefillDecodeCount).Should(gomega.Equal(6))
-			gomega.Expect(decodeOnlyCount).Should(gomega.Equal(0))
+			gomega.Expect(prefillDecodeCount).Should(gomega.Equal(4))
+			gomega.Expect(decodeOnlyCount).Should(gomega.Equal(2))
 
 			testutils.DeleteObjects(testConfig, epp)
 			testutils.DeleteObjects(testConfig, modelServers)
@@ -843,20 +843,24 @@ schedulingProfiles:
 // EPP configuration for running with P/D
 const pdConfig = `apiVersion: inference.networking.x-k8s.io/v1alpha1
 kind: EndpointPickerConfig
+featureGates:
+- prepareDataPlugins
 plugins:
 - type: prefill-header-handler
 - type: prefix-cache-scorer
   parameters:
-    blockSizeTokens: 10
+    blockSizeTokens: 4
     maxPrefixBlocksToMatch: 256
     lruCapacityPerServer: 256
 - type: prefill-filter
 - type: decode-filter
 - type: max-score-picker
+- type: prefix-based-pd-decider
+  parameters:
+    nonCachedTokens: 4
 - type: pd-profile-handler
   parameters:
-    hashBlockSize: 10
-    threshold: 40
+    deciderPluginName: prefix-based-pd-decider
 schedulingProfiles:
 - name: prefill
   plugins: