update readme

Author: tedzhouhk

components/backends/vllm/README.md

@@ -112,6 +112,7 @@ For Kubernetes deployment, YAML manifests are provided in the `deploy/` director
 - `agg_router.yaml` - Aggregated serving with KV routing
 - `disagg.yaml` - Disaggregated serving
 - `disagg_router.yaml` - Disaggregated serving with KV routing
+- `disagg_planner.yaml` - Disaggregated serving with [SLA Planner](../../../docs/architecture/sla_planner.md). See [SLA Planner Deployment Guide](../../../docs/guides/dynamo_deploy/sla_planner_deployment.md) for more details.
 
 #### Prerequisites
 
@@ -124,6 +125,8 @@ For Kubernetes deployment, YAML manifests are provided in the `deploy/` director
   # Update the image references in the YAML files
   ```
 
+- **Pre-Deployment Profiling (if Using SLA Planner)**: Follow the [pre-deployment profiling guide](../../../docs/architecture/pre_deployment_profiling.md) to run pre-deployment profiling. The results will be saved to the `profiling-pvc` PVC and queried by the SLA Planner.
+
 - **Port Forwarding**: After deployment, forward the frontend service to access the API:
   ```bash
   kubectl port-forward deployment/vllm-v1-disagg-frontend-<pod-uuid-info> 8080:8000

docs/architecture/pre_deployment_profiling.md

@@ -29,7 +29,7 @@ The script will recommend the best TP size for prefill and decode, as well as th
 2025-05-16 15:20:24 - __main__ - INFO - Suggested planner upper/lower bound for decode kv cache utilization: 0.20/0.10
 ```
 
-After finding the best TP size for prefill and decode, the script will then interpolate the TTFT with ISL and ITL with active KV cache and decode context length. This is to provide a more accurate estimation of the performance when ISL and OSL changes and will be used in the sla-planner. The results will be saved to `<output_dir>/<decode/prefill>_tp<best_tp>_interpolation`.
+After finding the best TP size for prefill and decode, the script will then interpolate the TTFT with ISL and ITL with active KV cache and decode context length. This is to provide a more accurate estimation of the performance when ISL and OSL changes and will be used in the sla-planner. The results will be saved to `<output_dir>/<decode/prefill>_tp<best_tp>_interpolation`. Please change the prefill and decode TP size in the config file to match the best TP sizes obtained from the profiling script.
 
 ### Prefill Interpolation Data
 

docs/architecture/sla_planner.md

@@ -8,7 +8,7 @@ The SLA (Service Level Agreement)-based planner is an intelligent autoscaling sy
 > Currently, SLA-based planner only supports disaggregated setup.
 
 > [!WARNING]
-> Bare metal deployment with local connector is deprecated. The only option to deploy SLA-based planner is via k8s. We will update the examples in this document soon.
+> Bare metal deployment with local connector is deprecated. Please deploy the SLA planner in k8s.
 
 ## Features
 
@@ -115,4 +115,4 @@ kubectl apply -f disagg_planner.yaml -n {$NAMESPACE}
 ```
 
 > [!NOTE]
-> The SLA planner requires a frontend that reports metrics at `/metrics` HTTP endpoint with number of requests, ISL, OSL, TTFT, ITL in the correct format. The VLLM frontend provides these metrics automatically.
+> The SLA planner requires a frontend that reports metrics at `/metrics` HTTP endpoint with number of requests, ISL, OSL, TTFT, ITL in the correct format. The dynamo frontend provides these metrics automatically.

docs/guides/dynamo_deploy/sla_planner_deployment.md

@@ -25,6 +25,8 @@ flowchart LR
 ## Prerequisites
 - Kubernetes cluster with GPU nodes
 - `hf-token-secret` created in target namespace
+- [Pre-Deployment Profiling](../../architecture/pre_deployment_profiling.md) results saved to `profiling-pvc` PVC.
+- Prefill and decode worker uses the best parallelization mapping suggested by the pre-deployment profiling script.
 
 ```bash
 export NAMESPACE=your-namespace