docs: Restructure profiling documentation around DGDR workflow (#3867)

Signed-off-by: Hannah Zhang <[email protected]>
Signed-off-by: Hongkuan Zhou <[email protected]>
Signed-off-by: hongkuanz <[email protected]>
Co-authored-by: Hongkuan Zhou <[email protected]>
Co-authored-by: hongkuanz <[email protected]>

Author: hhzhang16

README.md

@@ -179,7 +179,7 @@ Rerun with `curl -N` and change `stream` in the request to `true` to get the res
 Dynamo provides comprehensive benchmarking tools to evaluate and optimize your deployments:
 
 - **[Benchmarking Guide](docs/benchmarks/benchmarking.md)** – Compare deployment topologies (aggregated vs. disaggregated vs. vanilla vLLM) using AIPerf
-- **[Pre-Deployment Profiling](docs/benchmarks/pre_deployment_profiling.md)** – Optimize configurations before deployment to meet SLA requirements
+- **[SLA-Driven Dynamo Deployments](docs/planner/sla_planner_quickstart.md)** – Optimize your deployment to meet SLA requirements
 
 # Engines
 

components/backends/trtllm/deploy/README.md

@@ -53,7 +53,7 @@ Advanced disaggregated deployment with SLA-based automatic scaling.
 - `TRTLLMPrefillWorker`: Specialized prefill-only worker
 
 > [!NOTE]
-> This deployment requires pre-deployment profiling to be completed first. See [Pre-Deployment Profiling](../../../../docs/benchmarks/pre_deployment_profiling.md) for detailed instructions.
+> This deployment requires pre-deployment profiling to be completed first. See [Pre-Deployment Profiling](../../../../docs/benchmarks/sla_driven_profiling.md) for detailed instructions.
 
 ## CRD Structure
 

components/backends/vllm/deploy/README.md

@@ -99,7 +99,7 @@ We have public images available on [NGC Catalog](https://catalog.ngc.nvidia.com/
 
 ### Pre-Deployment Profiling (SLA Planner Only)
 
-If using the SLA Planner deployment (`disagg_planner.yaml`), follow the [pre-deployment profiling guide](../../../../docs/benchmarks/pre_deployment_profiling.md) to run pre-deployment profiling. The results will be saved to the `dynamo-pvc` PVC and queried by the SLA Planner.
+If using the SLA Planner deployment (`disagg_planner.yaml`), follow the [pre-deployment profiling guide](../../../../docs/benchmarks/sla_driven_profiling.md) to run pre-deployment profiling. The results will be saved to the `dynamo-pvc` PVC and queried by the SLA Planner.
 
 ## Usage
 

components/src/dynamo/planner/utils/perf_interpolation.py

@@ -28,7 +28,7 @@
 
 MISSING_PROFILING_DATA_ERROR_MESSAGE = (
     "SLA-Planner requires pre-deployment profiling results to run.\n"
-    "Please follow /docs/benchmarks/pre_deployment_profiling.md to run the profiling first,\n"
+    "Please follow /docs/benchmarks/sla_driven_profiling.md to run the profiling first,\n"
     "and make sure the profiling results are present in --profile-results-dir."
 )
 

deploy/utils/README.md

@@ -119,7 +119,7 @@ python3 -m deploy.utils.download_pvc_results \
 
 For complete benchmarking and profiling workflows:
 - **Benchmarking Guide**: See [docs/benchmarks/benchmarking.md](../../docs/benchmarks/benchmarking.md) for comparing DynamoGraphDeployments and external endpoints
-- **Pre-Deployment Profiling**: See [docs/benchmarks/pre_deployment_profiling.md](../../docs/benchmarks/pre_deployment_profiling.md) for optimizing configurations before deployment
+- **Pre-Deployment Profiling**: See [docs/benchmarks/sla_driven_profiling.md](../../docs/benchmarks/sla_driven_profiling.md) for optimizing configurations before deployment
 
 ## Notes
 

docs/benchmarks/pre_deployment_profiling.md

@@ -24,7 +24,7 @@ There are two additional rules set by planner to prevent over-compensation:
 
 ## SLA-based Scaling Up/Down Prefill/Decode Workers
 
-See [Pre-Deployment Profiling](../benchmarks/pre_deployment_profiling.md) for more details.
+See [SLA-Driven Profiling](../benchmarks/sla_driven_profiling.md) for more details.
 
 ## Usage
 

docs/benchmarks/sla_driven_profiling.md

@@ -78,5 +78,5 @@ Key features include:
 
    Overview <self>
    SLA Planner Quick Start <sla_planner_quickstart>
-   Pre-Deployment Profiling <../benchmarks/pre_deployment_profiling.md>
+   SLA-Driven Profiling <../benchmarks/sla_driven_profiling.md>
    SLA-based Planner <sla_planner.md>