diff --git a/demos/cuj2-demo.md b/demos/cuj2-demo.md
index 70871cf4a..b68938cbc 100644
--- a/demos/cuj2-demo.md
+++ b/demos/cuj2-demo.md
@@ -210,7 +210,7 @@ publication revalidate a private snapshot and publish only that inventory.
 │                                                                 │
 │  Discovery: Kubernetes-native (no etcd)                         │
 │  Requests:  Dynamo request plane (default TCP)                  │
-│  Events:    NATS event plane for worker KV-cache events         │
+│  Events:    ZMQ-based KV-cache event plane (direct, no NATS)    │
 │                                                                 │
 │  CRDs (6):                                                      │
 │  ├── DynamoGraphDeployment         (inference serving graph)    │
@@ -249,8 +249,8 @@ publication revalidate a private snapshot and publish only that inventory.
 │    1. Client → /v1/chat/completions → Frontend :8000            │
 │    2. Frontend → Dynamo request plane (TCP) → VllmDecodeWorker  │
 │    3. VllmDecodeWorker runs Qwen3-0.6B on H100                  │
-│    4. Worker relays local vLLM ZMQ KV events to NATS            │
-│    5. KV router consumes NATS events; response returns over TCP │
+│    4. Worker publishes ZMQ KV events directly to KV router      │
+│    5. KV router consumes ZMQ events; response returns over TCP  │
 └─────────────────────────────────────────────────────────────────┘
 ```
 ### ChatBot
diff --git a/demos/workloads/inference/vllm-agg.yaml b/demos/workloads/inference/vllm-agg.yaml
index 93c9da04d..b10c5f54f 100644
--- a/demos/workloads/inference/vllm-agg.yaml
+++ b/demos/workloads/inference/vllm-agg.yaml
@@ -75,7 +75,7 @@ spec:
               effect: NoExecute
           containers:
             - name: main
-              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.2.1
+              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.4.1
               env:
                 - name: SERVED_MODEL_NAME
                   value: Qwen/Qwen3-0.6B
@@ -103,7 +103,7 @@ spec:
               effect: NoSchedule
           containers:
             - name: main
-              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.2.1
+              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.4.1
               workingDir: /workspace/examples/backends/vllm
               command: ["python3", "-m", "dynamo.vllm"]
               args:
diff --git a/docs/contributor/validator.md b/docs/contributor/validator.md
index 78d1a2973..ae418d371 100644
--- a/docs/contributor/validator.md
+++ b/docs/contributor/validator.md
@@ -870,14 +870,14 @@ run-to-run TTFT fluctuation (see NVIDIA/aicr#1192):
   worker's active in-flight load so a transiently-slow worker stops receiving
   its full share — mitigating the stochastic EKS H100 worker-stall / throughput
   degradation at the saturation knee (issue #1197). Frontend-to-worker
-  requests use Dynamo's request plane (Dynamo 1.2 defaults to TCP; AICR does
-  not set `DYN_REQUEST_PLANE=nats`). Workers still publish local vLLM KV-cache
-  events through their ZMQ publisher (relayed onto the NATS event plane), but
-  least-loaded routing does not consume them.
+  requests use Dynamo's request plane (Dynamo 1.4+ defaults to TCP; AICR does
+  not set `DYN_REQUEST_PLANE=nats`). Workers publish KV-cache events directly
+  over ZMQ; the KV router consumes them end-to-end with no NATS relay.
+  Least-loaded routing does not consume those events.
   The `inference-routing-mode` recipe input defaults to `dynamo-router`; set
   `gateway-epp` to validate the GAIE/EPP path through agentgateway with worker
   frontend sidecars in direct mode. The direct-mode sidecars honor EPP routing
-  headers; they do not perform the ZMQ-to-NATS KV-event relay.
+  headers; they do not relay KV events.
 - **The AIPerf load generator co-locates with the GPU workers, but that is not
   resource contention.** It is CPU-only and the GPU node has ample CPU headroom
   (measured node CPU pressure ≈ 0 across runs); co-location does not starve the
diff --git a/docs/integrator/eks-dynamo-networking.md b/docs/integrator/eks-dynamo-networking.md
index 6c8fb3531..d10fdca7e 100644
--- a/docs/integrator/eks-dynamo-networking.md
+++ b/docs/integrator/eks-dynamo-networking.md
@@ -1,30 +1,44 @@
 # EKS Dynamo Networking Prerequisites
 
 For `*-eks-ubuntu-inference-dynamo` recipes, AICR configures
-`dynamo-platform` with Kubernetes-native discovery and the standard NATS
-event plane for KV-cache and runtime events:
-- `nats` on TCP `4222`
-
-This NATS dependency is new as of the Dynamo 1.2 bump, which switched discovery
-to the NATS event plane. A cluster whose system-node security group only
-allowlisted the pre-1.2 control-plane ports will not have `4222` open, so a
-bundle that worked on Dynamo 1.0.x can start failing purely from the version
-bump — add the `4222` rule below.
-
-Frontend-to-worker inference request/response traffic is separate: Dynamo 1.2
-defaults `DYN_REQUEST_PLANE` to TCP, and AICR does not override it to NATS. The
-worker runtime relays local vLLM ZMQ KV-cache events onto the NATS-backed event
-plane so the KV router or EPP can consume live cache state.
-
-If system components and GPU workloads are on different node groups/security groups, these ports may be blocked from GPU nodes to system nodes. Typical symptoms:
-- `JetStream not available` (NATS unreachable)
-- Dynamo frontend and vLLM worker pods stuck in `CrashLoopBackOff`, with
-  `Exception: Failed to connect to NATS: timed out` in the frontend log
-- Worker startup probes failing with `connection refused` because the process
-  exits before serving
-- The `inference-perf` performance validator failing after its workload-readiness
-  (10 min) and health (5 min) gates lapse — roughly 15 min — while `deployment`
-  and `conformance` pass; the workload never reaches a ready state
+`dynamo-platform` with Kubernetes-native discovery. As of the Dynamo 1.4+
+bump, AICR no longer installs bundled NATS by default: the request plane
+defaults to TCP and the KV event plane defaults to ZMQ
+(`ai-dynamo/dynamo#11951`). This removes the old `4222` NATS requirement,
+but it does **not** remove the underlying cross-nodegroup networking
+requirement — the request plane and KV events are now **direct
+frontend↔worker pod-to-pod connections** instead of both sides talking to a
+`dynamo-platform-nats` StatefulSet on the system nodegroup, and Frontend
+pods still run on the system nodegroup while workers run on the GPU
+nodegroup, so traffic still crosses the same GPU↔system nodegroup SG
+boundary as before.
+
+> **TODO before merging (tracked in NVIDIA/aicr#1836):** the port(s) below
+> are not yet confirmed against a real Dynamo 1.4+ EKS deployment. What's
+> known from the AICR recipes: the ZMQ KV-event endpoint is set explicitly
+> per worker via `--kv-events-config`, e.g.
+> `{"enable_kv_cache_events":true,"publisher":"zmq","endpoint":"tcp://*:5557"}`
+> (see `tests/manifests/dynamo-vllm-smoke-test.yaml`), offset by `+dp_rank`
+> for dp_rank > 0. The TCP request plane does not have one fixed,
+> documented port the way NATS had `4222` — confirm the actual listening
+> port(s) on a live cluster before finalizing the SG rule below:
+> ```shell
+> kubectl exec -n dynamo-system <frontend-pod> -- ss -tlnp
+> kubectl exec -n dynamo-system <worker-pod> -- ss -tlnp
+> ```
+
+If the GPU and system node groups sit in different security groups, these
+ports may be blocked from GPU nodes to the frontend's node (and vice versa).
+Typical symptoms:
+- Dynamo frontend and vLLM worker pods stuck in `CrashLoopBackOff`, or a
+  frontend that starts cleanly but never successfully routes a request
+  through to a worker
+- Worker startup probes failing with `connection refused` because the
+  process exits before serving
+- The `inference-perf` performance validator failing after its
+  workload-readiness (10 min) and health (5 min) gates lapse — roughly
+  15 min — while `deployment` and `conformance` pass; the workload never
+  reaches a ready state
 
 You can confirm reachability directly from a GPU node before re-running. The
 toleration is required because the GPU node groups on these clusters are
@@ -32,9 +46,9 @@ tainted (`NoSchedule`/`NoExecute`); without it the probe pod stays `Pending`
 and never runs:
 
 ```shell
-kubectl run nats-probe --rm -i --restart=Never --image=busybox:1.36 \
+kubectl run tcp-probe --rm -i --restart=Never --image=busybox:1.36 \
   --overrides='{"spec":{"nodeSelector":{"<gpu-node-label-key>":"<value>"},"tolerations":[{"operator":"Exists"}]}}' \
-  -- sh -c 'nc -zv -w 5 dynamo-platform-nats.dynamo-system.svc.cluster.local 4222'
+  -- sh -c 'nc -zv -w 5 <worker-pod-ip-or-svc> <PORT>'
 ```
 
 The conformance validator's `ai-service-metrics` check adds a third requirement:
@@ -64,8 +78,9 @@ SG rule below remains the reliable cluster-side guarantee.
 
 ## Required Security Group Rules
 
-Allow ingress from the GPU node security group to the system node security group on:
-- TCP `4222` - NATS event plane (dynamo-platform)
+Allow ingress from the GPU node security group to the system node security
+group on:
+- TCP `<PORT>` - Dynamo request plane + KV events (dynamo-platform) — confirm exact port(s) on-cluster, see TODO above
 - TCP `9090` - Prometheus (required for the `ai-service-metrics` conformance check)
 
 The `9090` rule is required as a fallback guarantee: the orchestrator *prefers*
@@ -94,9 +109,9 @@ aws ec2 describe-instances \
   --query "Reservations[0].Instances[0].SecurityGroups[*].GroupId" \
   --output text
 
-# 2) Allow NATS + Prometheus from GPU SG -> system SG
+# 2) Allow Dynamo request/event-plane + Prometheus from GPU SG -> system SG
 aws ec2 authorize-security-group-ingress --group-id <system-sg-id> \
-  --protocol tcp --port 4222 --source-group <gpu-sg-id>
+  --protocol tcp --port <PORT> --source-group <gpu-sg-id>
 
 aws ec2 authorize-security-group-ingress --group-id <system-sg-id> \
   --protocol tcp --port 9090 --source-group <gpu-sg-id>
diff --git a/docs/user/component-catalog.md b/docs/user/component-catalog.md
index e62bce2a2..005ad4f1c 100644
--- a/docs/user/component-catalog.md
+++ b/docs/user/component-catalog.md
@@ -32,7 +32,7 @@ The source of truth is [`recipes/registry.yaml`](https://github.com/NVIDIA/aicr/
 | **k8s-aibom** | Optional runtime AI workload inventory. Produces namespace-scoped CycloneDX 1.6 ML-BOM resources for explicitly opted-in namespaces. Installed by one stock recipe, `h100-gke-cos-inference`; every other stock recipe leaves it out. Decline it with `aicr recipe --runtime-inventory disabled`. CLI aliases: `k8saibom`, `aibom`. See [k8s-aibom Runtime Inventory](#k8s-aibom-runtime-inventory). | [k8s-aibom](https://github.com/GoogleCloudPlatform/k8s-aibom) |
 | **kai-scheduler** | Gang scheduler with hierarchical queues and topology-aware placement; works with device-plugin (`nvidia.com/gpu`) and DRA GPU allocation alike. Ensures distributed training jobs land on nodes with optimal interconnect topology. AICR pins `defaultQueue.createDefaultQueue: true`, so the chart creates the `default-parent-queue`/`default-queue` hierarchy on install. The `gang-scheduling` conformance check submits its synthetic test PodGroup to `default-queue` by name, so that queue is a hard dependency of validation, not an optional extra. Note the chart creates the queues only on first install and annotates them `helm.sh/resource-policy: keep` — a `helm upgrade` will not recreate them if they are deleted, so restore them manually (or reinstall the release) if that happens. Workloads are not restricted to this queue: Dynamo submits to its own `dynamo`/`dynamo-default` hierarchy, which its chart creates via post-install and post-upgrade hooks. | [KAI Scheduler](https://github.com/kai-scheduler/KAI-Scheduler) |
 | **grove** | Pod lifecycle management for Dynamo inference platform. Installed as a standalone component. | [Grove](https://github.com/ai-dynamo/grove) |
-| **dynamo-platform** | NVIDIA Dynamo inference serving platform with bundled CRDs. Distributed inference with KV-cache-aware routing, Dynamo request-plane traffic, a NATS-backed Kubernetes event plane for KV-cache events, and disaggregated prefill/decode. | [Dynamo](https://github.com/ai-dynamo/dynamo) |
+| **dynamo-platform** | NVIDIA Dynamo inference serving platform with bundled CRDs. Distributed inference with KV-cache-aware routing, Dynamo request-plane traffic, a ZMQ-based KV-cache event plane, and disaggregated prefill/decode. | [Dynamo](https://github.com/ai-dynamo/dynamo) |
 | **agentgateway-crds** | Custom Resource Definitions for agentgateway (Kubernetes Gateway API implementation for AI/ML inference). | [agentgateway](https://github.com/agentgateway/agentgateway) |
 | **agentgateway** | Kubernetes Gateway API implementation for AI/ML inference. Implements the Gateway API Inference Extension for model-aware ingress routing to InferencePool backends. | [agentgateway](https://github.com/agentgateway/agentgateway) |
 | **k8s-nim-operator** | NVIDIA NIM Operator for managing NIM (NVIDIA Inference Microservices) deployments on Kubernetes. AICR installs the operator only — it creates no `NIMService` and no credentials; see [NIM workload credentials](#nim-workload-credentials). | [K8s NIM Operator](https://github.com/NVIDIA/k8s-nim-operator) |
diff --git a/docs/user/container-images.md b/docs/user/container-images.md
index 112201971..0d27377a6 100644
--- a/docs/user/container-images.md
+++ b/docs/user/container-images.md
@@ -19,11 +19,11 @@ A machine-readable **CycloneDX 1.6 JSON** companion to this page is produced by
 <!-- BEGIN AICR-BOM -->
 ## Summary
 
-- Components: **44**
-- Unique images: **100**
-- Distinct registries: **11**
+- Components: **37**
+- Unique images: **88**
+- Distinct registries: **10**
 
-Registries: `602401143452.dkr.ecr.us-west-2.amazonaws.com`, `cr.agentgateway.dev`, `docker.io`, `gcr.io`, `ghcr.io`, `gke.gcr.io`, `nvcr.io`, `public.ecr.aws`, `quay.io`, `registry.k8s.io`, `us-docker.pkg.dev`
+Registries: `602401143452.dkr.ecr.us-west-2.amazonaws.com`, `cr.agentgateway.dev`, `docker.io`, `gcr.io`, `ghcr.io`, `gke.gcr.io`, `nvcr.io`, `quay.io`, `registry.k8s.io`, `us-docker.pkg.dev`
 
 _Rendering fidelity:_ `catalog-parity: charts are rendered with the shared recipes/components/<name>/values.yaml; per-recipe overlay overrides are not applied`
 
@@ -33,12 +33,10 @@ _Rendering fidelity:_ `catalog-parity: charts are rendered with the shared recip
 |-----------|------|-------|----------------|--------|
 | agentgateway | helm | agentgateway | v1.3.1 | 1 |
 | agentgateway-crds | helm | agentgateway-crds | v1.3.1 | 0 |
-| aws-ebs-csi-driver | helm | aws-ebs-csi-driver/aws-ebs-csi-driver | 2.59.0 | 6 |
+| aws-ebs-csi-driver | helm | aws-ebs-csi-driver/aws-ebs-csi-driver | 2.59.0 | 0 |
 | aws-efa | helm | aws-efa-k8s-device-plugin | v0.5.29 | 1 |
 | cert-manager | helm | jetstack/cert-manager | v1.20.2 | 4 |
-| cert-manager-ocp | manifest | — | — | 0 |
-| cert-manager-ocp-olm | manifest | — | — | 0 |
-| dynamo-platform | helm | dynamo-platform | 1.2.1 | 3 |
+| dynamo-platform | helm | dynamo-platform | 1.4.1 | 1 |
 | gatekeeper | helm | gatekeeper/gatekeeper | 3.22.2 | 3 |
 | gcp-driver-installer | manifest | — | — | 3 |
 | gke-nccl-tcpxo | manifest | — | — | 4 |
@@ -65,10 +63,8 @@ _Rendering fidelity:_ `catalog-parity: charts are rendered with the shared recip
 | nodewright-customizations | manifest | — | — | 5 |
 | nodewright-operator | helm | nodewright | v0.17.1 | 3 |
 | nvidia-dra-driver-gpu | helm | dra-driver-nvidia-gpu | 0.4.1 | 1 |
-| nvidia-dra-driver-gpu-ocp | helm | dra-driver-nvidia-gpu | 0.4.1 | 1 |
-| nvsentinel | helm | nvsentinel | v1.20.0 | 6 |
-| prometheus-adapter | helm | prometheus-community/prometheus-adapter | 5.3.0 | 1 |
-| prometheus-adapter-ocp | helm | prometheus-community/prometheus-adapter | 5.3.0 | 1 |
+| nvsentinel | helm | nvsentinel | v1.9.0 | 6 |
+| prometheus-adapter | helm | prometheus-community/prometheus-adapter | 5.3.0 | 0 |
 | prometheus-operator-crds | helm | prometheus-community/prometheus-operator-crds | 28.0.1 | 0 |
 | slinky-slurm | helm | slurm | 1.2.0 | 5 |
 | slinky-slurm-operator | helm | slurm-operator | 1.2.0 | 2 |
@@ -97,12 +93,9 @@ _No images extracted._
 
 ### aws-ebs-csi-driver
 
-- `public.ecr.aws/csi-components/csi-attacher:v4.11.0-eksbuild.4`
-- `public.ecr.aws/csi-components/csi-node-driver-registrar:v2.16.0-eksbuild.4`
-- `public.ecr.aws/csi-components/csi-provisioner:v6.2.0-eksbuild.3`
-- `public.ecr.aws/csi-components/csi-resizer:v2.1.0-eksbuild.4`
-- `public.ecr.aws/csi-components/livenessprobe:v2.18.0-eksbuild.4`
-- `public.ecr.aws/ebs-csi-driver/aws-ebs-csi-driver:v1.59.0`
+> Warning: [INTERNAL] helm template failed: signal: killed
+
+_No images extracted._
 
 ### aws-efa
 
@@ -125,9 +118,7 @@ _No images extracted._
 
 ### dynamo-platform
 
-- `nats:2.10.21-alpine`
-- `natsio/nats-server-config-reloader:0.16.0`
-- `nvcr.io/nvidia/ai-dynamo/kubernetes-operator:1.2.1`
+- `nvcr.io/nvidia/ai-dynamo/kubernetes-operator:1.4.1`
 
 ### gatekeeper
 
@@ -298,7 +289,9 @@ _No images extracted._
 
 ### prometheus-adapter
 
-- `registry.k8s.io/prometheus-adapter/prometheus-adapter:v0.12.0`
+> Warning: [INTERNAL] helm template failed: signal: killed
+
+_No images extracted._
 
 ### prometheus-adapter-ocp
 
diff --git a/docs/user/validation.md b/docs/user/validation.md
index 936497bd2..702acac0e 100644
--- a/docs/user/validation.md
+++ b/docs/user/validation.md
@@ -382,14 +382,13 @@ default `dynamo-router` mode deploys a Dynamo frontend with load-aware
 least-loaded routing (`DYN_ROUTER_MODE=least-loaded`), which balances by each
 worker's active in-flight load so a transiently-slow worker stops receiving its
 full share (see issue #1197). Normal frontend-to-worker request/response traffic
-uses Dynamo's request plane (Dynamo 1.2 defaults to TCP); AICR does not set
-`DYN_REQUEST_PLANE=nats`. Workers still run the vLLM ZMQ KV-cache event
-publisher relayed onto the NATS event plane, but least-loaded routing does not
-consume those events. Set it to `gateway-epp`
+uses Dynamo's request plane (Dynamo 1.4+ defaults to TCP); AICR does not set
+`DYN_REQUEST_PLANE=nats`. Workers publish KV-cache events directly over ZMQ;
+the KV router consumes them end-to-end with no NATS relay. Set it to `gateway-epp`
 to exercise GAIE/EPP: the validator deploys an EPP component, worker frontend
 sidecars in direct mode, and an HTTPRoute through the AICR-managed inference
-gateway. The direct-mode sidecars honor EPP routing headers; they are not the
-ZMQ-to-NATS relay.
+gateway. The direct-mode sidecars honor EPP routing headers; they do not
+relay KV events.
 
 **Model-weights cache and `AICR_INFERENCE_PERF_MODEL_CACHE_STORAGE_CLASS`.** The benchmark downloads
 the model **once** into a PVC and serves all workers from it (on by default;
diff --git a/pkg/bundler/bundler_test.go b/pkg/bundler/bundler_test.go
index 04fcec2cb..cb15459a5 100644
--- a/pkg/bundler/bundler_test.go
+++ b/pkg/bundler/bundler_test.go
@@ -2365,74 +2365,6 @@ func TestApplyNodeSchedulingOverrides_StorageClass(t *testing.T) {
 	}
 }
 
-func TestApplyNodeSchedulingOverrides_DynamoPlatformStorageClass(t *testing.T) {
-	const scPath = "nats.config.jetstream.fileStore.pvc.storageClassName"
-
-	registry, err := recipe.GetComponentRegistry()
-	if err != nil {
-		t.Fatalf("GetComponentRegistry() error = %v", err)
-	}
-	comp := registry.Get("dynamo-platform")
-	if comp == nil {
-		t.Fatal("registry missing dynamo-platform")
-	}
-	if !slices.Contains(comp.GetStorageClassPaths(), scPath) {
-		t.Fatalf("registry storageClassPaths for dynamo-platform = %v, want %q",
-			comp.GetStorageClassPaths(), scPath)
-	}
-
-	tests := []struct {
-		name          string
-		cfgOpts       []config.Option
-		initialValues map[string]string
-		wantValue     string
-	}{
-		{
-			name:      "global storageClass injected into bundled NATS PVC",
-			cfgOpts:   []config.Option{config.WithStorageClass("my-storage-class")},
-			wantValue: "my-storage-class",
-		},
-		{
-			name: "explicit dynamo --set wins over global --storage-class",
-			cfgOpts: []config.Option{
-				config.WithStorageClass("my-storage-class"),
-				config.WithValueOverrides(map[string]map[string]string{
-					"dynamo": {scPath: "explicit-gp2"},
-				}),
-			},
-			initialValues: map[string]string{scPath: "explicit-gp2"},
-			wantValue:     "explicit-gp2",
-		},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			cfg := config.NewConfig(tt.cfgOpts...)
-			b, err := New(WithConfig(cfg))
-			if err != nil {
-				t.Fatalf("New() error = %v", err)
-			}
-
-			values := map[string]any{}
-			if len(tt.initialValues) > 0 {
-				if applyErr := component.ApplyMapOverrides(values, tt.initialValues); applyErr != nil {
-					t.Fatalf("ApplyMapOverrides() setup error = %v", applyErr)
-				}
-			}
-
-			b.applyNodeSchedulingOverrides("dynamo-platform", values, nil, schedulingPathPolicy{})
-
-			got, ok := component.GetValueByPath(values, scPath)
-			if !ok {
-				t.Fatal("storageClassName not injected")
-			}
-			if got != tt.wantValue {
-				t.Errorf("storageClassName = %v, want %q", got, tt.wantValue)
-			}
-		})
-	}
-}
-
 // TestApplyNodeSchedulingOverrides_RespectsRecipeSetPaths verifies the
 // precedence rule that paths the user explicitly populated via the recipe
 // overlay's inline overrides or CLI --set are NOT overwritten by CLI/config
@@ -3029,76 +2961,6 @@ func TestWarnMissingStorageClassForPVCs(t *testing.T) {
 	}
 }
 
-func TestWarnMissingStorageClassForPVCs_DynamoPlatformNATS(t *testing.T) {
-	const scPath = "nats.config.jetstream.fileStore.pvc.storageClassName"
-
-	recipeResult := &recipe.RecipeResult{
-		ComponentRefs: []recipe.ComponentRef{{
-			Name:       "dynamo-platform",
-			ValuesFile: "components/dynamo-platform/values.yaml",
-		}},
-	}
-
-	tests := []struct {
-		name        string
-		setupValues func(map[string]any)
-		wantWarning bool
-	}{
-		{
-			name:        "warns when bundled NATS PVC omits storageClassName",
-			wantWarning: true,
-		},
-		{
-			name: "does not warn when bundled NATS PVC has storageClassName",
-			setupValues: func(values map[string]any) {
-				component.SetValueByPath(values, scPath, "gp3")
-			},
-		},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			values, err := recipeResult.GetValuesForComponent("dynamo-platform")
-			if err != nil {
-				t.Fatalf("GetValuesForComponent(dynamo-platform): %v", err)
-			}
-			if tt.setupValues != nil {
-				tt.setupValues(values)
-			}
-
-			b, err := New()
-			if err != nil {
-				t.Fatalf("New() error = %v", err)
-			}
-
-			err = b.warnMissingStorageClassForPVCs(context.Background(), recipeResult, map[string]map[string]any{
-				"dynamo-platform": values,
-			})
-			if err != nil {
-				t.Fatalf("warnMissingStorageClassForPVCs() error = %v", err)
-			}
-
-			if gotWarning := len(b.warnings) > 0; gotWarning != tt.wantWarning {
-				t.Fatalf("warning present = %v, want %v; warnings = %v", gotWarning, tt.wantWarning, b.warnings)
-			}
-
-			if tt.wantWarning {
-				warning := b.warnings[0]
-				for _, want := range []string{
-					"Warning: dynamo-platform renders a PVC without storageClassName",
-					scPath,
-					"--storage-class <name>",
-					"--set dynamo-platform:" + scPath + "=<name>",
-				} {
-					if !strings.Contains(warning, want) {
-						t.Errorf("warning = %q, want substring %q", warning, want)
-					}
-				}
-			}
-		})
-	}
-}
-
 // TestAgentgatewayComponentExistsInRegistry locks agentgatewayComponentName to a
 // real registry entry. resolveAgentgatewayExposure keys into componentValues by
 // this name; if the "agentgateway" component were renamed in recipes/registry.yaml,
diff --git a/pkg/evidence/cncf/scripts/collect-evidence.sh b/pkg/evidence/cncf/scripts/collect-evidence.sh
index fa128fd86..e82c0ba17 100755
--- a/pkg/evidence/cncf/scripts/collect-evidence.sh
+++ b/pkg/evidence/cncf/scripts/collect-evidence.sh
@@ -2860,9 +2860,8 @@ webhooks operational, and custom resources reconciled.
 2. **Custom Resource Definitions** — 6 Dynamo CRDs registered (DynamoGraphDeployment, DynamoComponentDeployment, etc.)
 3. **Webhooks Operational** — a webhook-invalid DynamoGraphDeployment must be rejected with a webhook-attributed message
 4. **Custom Resource Reconciled** — `DynamoGraphDeployment/vllm-agg` reconciled into running workload pods via PodCliques
-5. **Supporting Services** — NATS running for Dynamo's Kubernetes event plane
-
-The result is stated by the verdict line at the end of this section, after the checks run.
+5. **Supporting Services** — ZMQ-based KV-cache event plane (no NATS; Dynamo 1.4+ default)
+6. **Result: PASS**
 
 ---
 
diff --git a/pkg/evidence/cncf/scripts/manifests/dynamo-vllm-agg.yaml b/pkg/evidence/cncf/scripts/manifests/dynamo-vllm-agg.yaml
index d1f487815..0cc3abfc9 100644
--- a/pkg/evidence/cncf/scripts/manifests/dynamo-vllm-agg.yaml
+++ b/pkg/evidence/cncf/scripts/manifests/dynamo-vllm-agg.yaml
@@ -82,7 +82,7 @@ spec:
               effect: NoExecute
           containers:
             - name: main
-              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.2.1
+              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.4.1
               env:
                 - name: SERVED_MODEL_NAME
                   value: Qwen/Qwen3-0.6B
@@ -110,7 +110,7 @@ spec:
               effect: NoSchedule
           containers:
             - name: main
-              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.2.1
+              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.4.1
               workingDir: /workspace/examples/backends/vllm
               command: ["python3", "-m", "dynamo.vllm"]
               args:
diff --git a/recipes/components/dynamo-platform/values.yaml b/recipes/components/dynamo-platform/values.yaml
index e6fbeece9..268bf7f25 100644
--- a/recipes/components/dynamo-platform/values.yaml
+++ b/recipes/components/dynamo-platform/values.yaml
@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-# Dynamo Platform Helm values (v1.2.1)
+# Dynamo Platform Helm values (v1.4.1)
 # NVIDIA Dynamo inference serving platform operator.
 # Provides OpenAI-compatible endpoints, KV-cache-aware routing,
 # disaggregated prefill/decode, and SLA-driven autoscaling.
@@ -23,13 +23,18 @@ global:
   # Kubernetes-native discovery replaces etcd for AICR Dynamo workloads.
   etcd:
     install: false
-  # Dynamo 1.2 defaults the runtime event plane to NATS for distributed
-  # Kubernetes backends. Install the bundled NATS chart so workloads can use
-  # the runtime default instead of per-workload DYN_EVENT_PLANE overrides.
-  # Request/response traffic stays on Dynamo's request plane default (TCP)
-  # unless a workload explicitly sets DYN_REQUEST_PLANE.
-  nats:
-    install: true
+  # Dynamo 1.4+ defaults the request plane to TCP and the KV event plane to
+  # ZMQ, so the bundled NATS chart is no longer needed for AICR's defaults.
+  # global.nats.install is intentionally left unset (chart default: false).
+  # Re-enable only if a workload explicitly opts into a NATS-based transport
+  # (legacy DYN_REQUEST_PLANE=nats, DYN_EVENT_PLANE=nats, or a NATS
+  # request-trace sink), via global.nats.install: true.
+  #
+  # Upgrade note: on an in-place `helm upgrade` of a standing cluster,
+  # accepting this default removes bundled NATS and drops NATS_SERVER from
+  # operator-managed workload specs, which triggers rolling restarts. Fresh
+  # bundle installs are unaffected. Pass --set global.nats.install=true
+  # during the upgrade to opt out and avoid the restart.
   # Disable kai-scheduler sub-chart install — managed as a separate AICR component.
   # Keep enabled: true so the Dynamo operator detects and uses the external scheduler.
   kai-scheduler:
@@ -41,17 +46,6 @@ global:
     install: false
     enabled: true
 
-nats:
-  config:
-    jetstream:
-      fileStore:
-        pvc:
-          # Mirror the chart default so AICR can warn when no StorageClass is
-          # selected and inject --storage-class into the bundled NATS PVC.
-          enabled: true
-          size: 10Gi
-          storageClassName: ""
-
 dynamo-operator:
   # Upgrade CRDs via the platform chart (no separate dynamo-crds 1.0 chart)
   upgradeCRD: true
@@ -63,4 +57,4 @@ dynamo-operator:
   # PodMonitor CRs are auto-created by the operator for metric discovery.
   dynamo:
     metrics:
-      prometheusEndpoint: "http://kube-prometheus-prometheus.monitoring.svc.cluster.local:9090"
+      prometheusEndpoint: "http://kube-prometheus-prometheus.monitoring.svc.cluster.local:9090"
\ No newline at end of file
diff --git a/recipes/registry.yaml b/recipes/registry.yaml
index abbf297a2..486f32097 100644
--- a/recipes/registry.yaml
+++ b/recipes/registry.yaml
@@ -613,18 +613,14 @@ components:
     helm:
       defaultRepository: https://helm.ngc.nvidia.com/nvidia/ai-dynamo
       defaultChart: dynamo-platform
-      defaultVersion: "1.2.1"
+      defaultVersion: "1.4.1"
       defaultNamespace: dynamo-system
-    storageClassPaths:
-      - nats.config.jetstream.fileStore.pvc.storageClassName
     nodeScheduling:
       system:
         nodeSelectorPaths:
           - dynamo-operator.controllerManager.nodeSelector
-          - nats.podTemplate.merge.spec.nodeSelector
         tolerationPaths:
           - dynamo-operator.controllerManager.tolerations
-          - nats.podTemplate.merge.spec.tolerations
 
   - name: agentgateway-crds
     displayName: agentgateway-crds
diff --git a/tests/chainsaw/ai-conformance/README.md b/tests/chainsaw/ai-conformance/README.md
index 017597b82..c133f0d80 100644
--- a/tests/chainsaw/ai-conformance/README.md
+++ b/tests/chainsaw/ai-conformance/README.md
@@ -163,7 +163,7 @@ chainsaw test \
 | Namespaces, CRDs | 2m | Should exist immediately after deployment |
 | cert-manager, agentgateway, skyhook, monitoring, kai-scheduler | 5m | Standard Deployment rollout |
 | gpu-operator, nvidia-dra-driver-gpu | 10m | GPU driver compilation on nodes is slow |
-| dynamo-platform | 5m | Operator + Grove + NATS event-plane startup |
+| dynamo-platform | 5m | Operator + Grove startup |
 
 ## Assertion Patterns
 
diff --git a/tests/chainsaw/ai-conformance/cluster/assert-dynamo.yaml b/tests/chainsaw/ai-conformance/cluster/assert-dynamo.yaml
index a5037510c..a6e6a9d8f 100644
--- a/tests/chainsaw/ai-conformance/cluster/assert-dynamo.yaml
+++ b/tests/chainsaw/ai-conformance/cluster/assert-dynamo.yaml
@@ -13,12 +13,13 @@
 # limitations under the License.
 
 # Assert Dynamo platform components are healthy.
-# Chart: dynamo-platform 1.2.1
+# Chart: dynamo-platform 1.4.1
 # Provides NVIDIA Dynamo inference serving: OpenAI-compatible endpoints,
 # KV-cache-aware routing, disaggregated prefill/decode, SLA-driven autoscaling.
 #
-# AICR uses Kubernetes-native discovery, so etcd remains disabled. NATS is
-# enabled for Dynamo's Kubernetes event plane and worker KV-cache events.
+# AICR uses Kubernetes-native discovery, so etcd remains disabled. As of
+# Dynamo 1.4+, the request plane defaults to TCP and the KV event plane to
+# ZMQ, so bundled NATS is no longer installed by default (NVIDIA/aicr#1836).
 
 # Dynamo Operator — manages DynamoComponent and DynamoGraphDeployment CRs
 apiVersion: apps/v1
@@ -30,15 +31,6 @@ status:
   (conditions[?type == 'Available']):
     - status: "True"
 ---
-# NATS — event plane used by Dynamo KV-cache-aware routing on Kubernetes
-apiVersion: apps/v1
-kind: StatefulSet
-metadata:
-  name: dynamo-platform-nats
-  namespace: dynamo-system
-status:
-  (readyReplicas > `0`): true
----
 # Grove Operator — pod lifecycle management for DynamoGraphDeployments
 apiVersion: apps/v1
 kind: Deployment
diff --git a/tests/chainsaw/ai-conformance/cluster/chainsaw-test.yaml b/tests/chainsaw/ai-conformance/cluster/chainsaw-test.yaml
index d858f14b1..c19893381 100644
--- a/tests/chainsaw/ai-conformance/cluster/chainsaw-test.yaml
+++ b/tests/chainsaw/ai-conformance/cluster/chainsaw-test.yaml
@@ -116,7 +116,7 @@ spec:
 
     # ── Dynamo Platform ────────────────────────────────────────────────
     - name: assert-dynamo
-      description: Verify Dynamo operator, Grove, and NATS event plane are healthy.
+      description: Verify Dynamo operator and Grove are healthy.
       try:
         - assert:
             file: assert-dynamo.yaml
diff --git a/tests/chainsaw/ai-conformance/kind-inference-dynamo/assert-dynamo.yaml b/tests/chainsaw/ai-conformance/kind-inference-dynamo/assert-dynamo.yaml
index 9401afa0a..04c9153a4 100644
--- a/tests/chainsaw/ai-conformance/kind-inference-dynamo/assert-dynamo.yaml
+++ b/tests/chainsaw/ai-conformance/kind-inference-dynamo/assert-dynamo.yaml
@@ -13,8 +13,9 @@
 # limitations under the License.
 
 # Assert Dynamo platform components are healthy on the kind inference stack.
-# AICR uses Kubernetes-native discovery plus NATS for Dynamo's Kubernetes
-# event plane and worker KV-cache events.
+# AICR uses Kubernetes-native discovery. As of Dynamo 1.4+, the request
+# plane defaults to TCP and the KV event plane to ZMQ, so bundled NATS is
+# no longer installed by default (NVIDIA/aicr#1836).
 apiVersion: apps/v1
 kind: Deployment
 metadata:
@@ -25,14 +26,6 @@ status:
     - status: "True"
 ---
 apiVersion: apps/v1
-kind: StatefulSet
-metadata:
-  name: dynamo-platform-nats
-  namespace: dynamo-system
-status:
-  (readyReplicas > `0`): true
----
-apiVersion: apps/v1
 kind: Deployment
 metadata:
   name: grove-operator
diff --git a/tests/chainsaw/ai-conformance/kind-inference-dynamo/chainsaw-test.yaml b/tests/chainsaw/ai-conformance/kind-inference-dynamo/chainsaw-test.yaml
index eefb665ad..d8e0b87b0 100644
--- a/tests/chainsaw/ai-conformance/kind-inference-dynamo/chainsaw-test.yaml
+++ b/tests/chainsaw/ai-conformance/kind-inference-dynamo/chainsaw-test.yaml
@@ -118,7 +118,7 @@ spec:
 
     # ── Dynamo Platform ────────────────────────────────────────────────
     - name: assert-dynamo
-      description: Verify Dynamo operator, Grove, and NATS event plane are healthy.
+      description: Verify Dynamo operator and Grove are healthy.
       try:
         - assert:
             file: assert-dynamo.yaml
diff --git a/tests/manifests/dynamo-vllm-smoke-test.yaml b/tests/manifests/dynamo-vllm-smoke-test.yaml
index 6497a8bcb..da1ff09bd 100644
--- a/tests/manifests/dynamo-vllm-smoke-test.yaml
+++ b/tests/manifests/dynamo-vllm-smoke-test.yaml
@@ -20,11 +20,11 @@
 # serving Qwen/Qwen3-0.6B (public, ungated, ~1.2GB).
 # No HuggingFace token required.
 #
-# Uses the Dynamo 1.2 Kubernetes path: Kubernetes-native discovery plus the
-# NATS-backed event plane from the dynamo-platform chart. Request/response
-# traffic uses Dynamo's request plane default (TCP). The frontend runs
-# KV-cache-aware routing; the local vLLM engine publishes KV events through
-# ZMQ and the Dynamo worker runtime relays them onto the NATS event plane.
+# Uses the Dynamo 1.4+ Kubernetes path: Kubernetes-native discovery, with
+# the request plane on TCP (default) and the KV event plane on ZMQ
+# (default) — no bundled NATS relay in between. The frontend runs
+# KV-cache-aware routing; the local vLLM engine publishes KV events over
+# ZMQ and the KV router consumes them directly, end-to-end.
 #
 # Usage:
 #   kubectl apply -f tests/manifests/dynamo-vllm-smoke-test.yaml -n dynamo-system
@@ -49,12 +49,16 @@ spec:
         spec:
           containers:
             - name: main
-              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.2.1
+              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.4.1
               env:
                 - name: SERVED_MODEL_NAME
                   value: Qwen/Qwen3-0.6B
                 - name: DYN_ROUTER_MODE
                   value: kv
+                - name: DYN_REQUEST_PLANE
+                  value: tcp
+                - name: DYN_EVENT_PLANE
+                  value: zmq
     - name: VllmDecodeWorker
       type: worker
       replicas: 1
@@ -67,9 +71,14 @@ spec:
               effect: NoSchedule
           containers:
             - name: main
-              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.2.1
+              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.4.1
               workingDir: /workspace/examples/backends/vllm
               command: ["python3", "-m", "dynamo.vllm"]
+              env:
+                - name: DYN_REQUEST_PLANE
+                  value: tcp
+                - name: DYN_EVENT_PLANE
+                  value: zmq
               args:
                 - --model
                 - Qwen/Qwen3-0.6B
diff --git a/tests/uat/lib/phases.sh b/tests/uat/lib/phases.sh
index 2229a9fad..327e6cec1 100644
--- a/tests/uat/lib/phases.sh
+++ b/tests/uat/lib/phases.sh
@@ -162,12 +162,10 @@ SERVE_NAMESPACE="${SERVE_NAMESPACE:-dynamo-workload}"
 SERVE_NAME="${SERVE_NAME:-vllm-agg}"
 SERVE_QUEUE="${SERVE_QUEUE:-dynamo}"
 SERVE_MODEL="${SERVE_MODEL:-Qwen/Qwen3-0.6B}"
-SERVE_RUNTIME_IMAGE="${SERVE_RUNTIME_IMAGE:-nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.2.1}"
-# GPU pool placement, applied to BOTH graph components (#1644 — it keeps the
-# Frontend off the small CPU nodes, where its ~12GB image pull blew the
-# readiness budget). The demo pins nodeGroup=gpu-worker; every UAT cluster
-# labels its GPU pool the same way (tests/uat/*/cluster-config.yaml), so the
-# default lands the graph on the GPU pool on any of the clouds.
+SERVE_RUNTIME_IMAGE="${SERVE_RUNTIME_IMAGE:-nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.4.1}"
+# GPU worker placement. The demo pins nodeGroup=gpu-worker; both UAT clusters
+# label their GPU pool the same way (tests/uat/*/cluster-config.yaml), so the
+# default lands the decode worker on the GPU node on either cloud.
 SERVE_GPU_NODE_SELECTOR_KEY="${SERVE_GPU_NODE_SELECTOR_KEY:-nodeGroup}"
 SERVE_GPU_NODE_SELECTOR_VALUE="${SERVE_GPU_NODE_SELECTOR_VALUE:-gpu-worker}"
 SERVE_FRONTEND_PORT="${SERVE_FRONTEND_PORT:-8000}"
diff --git a/validators/performance/inference_perf_constraint.go b/validators/performance/inference_perf_constraint.go
index 9da3fab94..592954765 100644
--- a/validators/performance/inference_perf_constraint.go
+++ b/validators/performance/inference_perf_constraint.go
@@ -2746,7 +2746,7 @@ func resolveModel(ctx *validators.Context) string {
 // `gateway-epp` switches to Gateway API Inference Extension: EPP
 // performs KV-aware endpoint selection and worker frontend sidecars run in
 // direct mode so they honor EPP's routing headers. The sidecars do not relay
-// local vLLM ZMQ KV events onto NATS; that relay is handled by the worker
+// KV events; workers publish ZMQ KV events directly to the KV router.
 // runtime.
 func resolveRoutingMode(ctx *validators.Context) (inferenceRoutingMode, error) {
 	if c, ok := findPerformanceConstraint(ctx, perfConstraintRoutingMode); ok {
diff --git a/validators/performance/model_cache.go b/validators/performance/model_cache.go
index 229b46987..e6da370a0 100644
--- a/validators/performance/model_cache.go
+++ b/validators/performance/model_cache.go
@@ -101,7 +101,7 @@ const (
 	// ResolveImage for registry-override parity is tracked in #1159. Note that
 	// registry parity alone is not air-gap support: the populate Job's
 	// snapshot_download still reaches huggingface.co for the weights.
-	cacheWorkerImage = "nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.2.1"
+	cacheWorkerImage = "nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.4.1"
 
 	// Resource requests for the populate container. snapshot_download is
 	// network/IO-bound, not compute-bound, so requests stay small; they exist so
diff --git a/validators/performance/testdata/inference/dynamo-deployment-gateway-epp.yaml b/validators/performance/testdata/inference/dynamo-deployment-gateway-epp.yaml
index 88c11ab44..a7be0bf98 100644
--- a/validators/performance/testdata/inference/dynamo-deployment-gateway-epp.yaml
+++ b/validators/performance/testdata/inference/dynamo-deployment-gateway-epp.yaml
@@ -15,8 +15,8 @@
 # Dynamo inference workload for performance benchmarking through GAIE/EPP.
 # EPP performs KV-cache-aware endpoint selection and worker frontend sidecars
 # run in direct mode so they honor EPP's routing headers. Direct mode is not
-# the local ZMQ-to-NATS relay; the Dynamo worker runtime relays vLLM KV-cache
-# events from the local ZMQ publisher onto the NATS-backed event plane.
+# workers publish KV-cache events over ZMQ directly to the KV router;
+# no NATS relay in the 1.4+ default path.
 #
 # Worker GPU wiring is MODE-DISPATCHED (capability-driven, issue #1327): DRA
 # ResourceClaimTemplate on nodes with usable full-GPU DRA, device-plugin
@@ -41,7 +41,7 @@ spec:
         spec:
           containers:
             - name: main
-              image: nvcr.io/nvidia/ai-dynamo/epp-image:1.2.1
+              image: nvcr.io/nvidia/ai-dynamo/epp-image:1.4.1
               env:
                 - name: DYN_KV_CACHE_BLOCK_SIZE
                   value: "128"
@@ -96,7 +96,7 @@ spec:
         spec:
           containers:
             - name: main
-              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.2.1
+              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.4.1
               workingDir: /workspace/examples/backends/vllm
               # Shell wrapper appends GKE's managed-device-plugin driver-lib
               # mount (/usr/local/nvidia/lib64) to LD_LIBRARY_PATH — the
@@ -134,7 +134,7 @@ spec:
                       key: token
                       optional: true
             - name: sidecar-frontend
-              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.2.1
+              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.4.1
               args:
                 - -m
                 - dynamo.frontend
diff --git a/validators/performance/testdata/inference/dynamo-deployment.yaml b/validators/performance/testdata/inference/dynamo-deployment.yaml
index 07e12d4ca..e7ea81e59 100644
--- a/validators/performance/testdata/inference/dynamo-deployment.yaml
+++ b/validators/performance/testdata/inference/dynamo-deployment.yaml
@@ -16,8 +16,8 @@
 # Deploys a vLLM aggregated backend with a small model for smoke testing.
 # Worker replicas scale to match available GPUs (1 GPU per replica).
 # Frontend-to-worker traffic uses Dynamo's request plane default (TCP). The
-# local vLLM ZMQ KV-event publisher feeds the worker runtime, which relays
-# KV-cache events onto the NATS-backed Dynamo event plane.
+# local vLLM ZMQ KV-event publisher feeds the KV router directly;
+# no NATS relay in the 1.4+ default path.
 #
 # Worker GPU wiring is MODE-DISPATCHED (capability-driven, issue #1327): on
 # nodes with usable full-GPU DRA the workers bind a DRA ResourceClaimTemplate
@@ -45,7 +45,7 @@ spec:
         spec:
           containers:
             - name: main
-              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.2.1
+              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.4.1
               env:
                 - name: SERVED_MODEL_NAME
                   # Quoted so a scalar-looking model ID (e.g. a pure-numeric or
@@ -84,7 +84,7 @@ spec:
         spec:
           containers:
             - name: main
-              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.2.1
+              image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.4.1
               workingDir: /workspace/examples/backends/vllm
               # GKE's managed device plugin (the gke-default gpuStack value)
               # mounts the node's driver tree at /usr/local/nvidia via its