docs: add mention of deploy/utils quickstart to planner deployment docs (#2821)

Signed-off-by: Hannah Zhang <hannahz@nvidia.com>

docs/architecture/sla_planner.md

@@ -28,7 +28,9 @@ The SLA planner consists of several key components:
 
 ## Pre-Deployment Profiling
 
-SLA-based planner requires pre-deployment profiling to operate. See [Pre-Deployment Profiling](../benchmarks/pre_deployment_profiling.md) for more details.
+**Prerequisite**: SLA-based planner requires pre-deployment profiling to be completed before deployment. The profiling process analyzes your model's performance characteristics to determine optimal tensor parallelism configurations and scaling parameters that the planner will use during operation.
+
+See [Pre-Deployment Profiling](../benchmarks/pre_deployment_profiling.md) for detailed instructions on running the profiling process.
 
 ## Load Prediction
 

docs/guides/dynamo_deploy/sla_planner_deployment.md

@@ -23,10 +23,11 @@ flowchart LR
 
 ## Prerequisites
 - Kubernetes cluster with GPU nodes
-- `hf-token-secret` created in target namespace
-- [Pre-Deployment Profiling](../../benchmarks/pre_deployment_profiling.md) results saved to `dynamo-pvc` PVC.
+- [Pre-Deployment Profiling](../../benchmarks/pre_deployment_profiling.md) completed and its results saved to `dynamo-pvc` PVC.
 - Prefill and decode worker uses the best parallelization mapping suggested by the pre-deployment profiling script.
 
+> [!NOTE]
+> **Important**: The profiling that occurs before Planner deployment requires additional Kubernetes manifests (ServiceAccount, Role, RoleBinding, PVC) that are not included in standard Dynamo deployments. Apply these manifests in the same namespace as `$NAMESPACE`. For a complete setup, start with the [Quick Start guide](../../../deploy/utils/README.md#quick-start), which provides a fully encapsulated deployment including all required manifests.
 ```bash
 export NAMESPACE=your-namespace
 ```