base: 35 RPS; safety, 75 RPS

# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan

docs/source/distributions/k8s-benchmark/perf_test_config.yaml

@@ -0,0 +1,19 @@
+version: '2'
+image_name: perf-test-demo
+apis:
+- inference
+providers:
+  inference:
+  - provider_id: vllm-inference
+    provider_type: remote::vllm
+    config:
+      url: ${env.VLLM_URL:=http://localhost:8001/v1}
+      max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
+      api_token: ${env.VLLM_API_TOKEN:=fake}
+      tls_verify: ${env.VLLM_TLS_VERIFY:=false}
+models:
+- model_id: ${env.INFERENCE_MODEL}
+  provider_id: vllm-inference
+  model_type: llm
+server:
+  port: 8322

docs/source/distributions/k8s-benchmark/stack_run_config.yaml

@@ -3,6 +3,7 @@ image_name: kubernetes-benchmark-demo
 apis:
 - agents
 - inference
+- safety
 - telemetry
 - tool_runtime
 - vector_io
@@ -30,6 +31,11 @@ providers:
         db: ${env.POSTGRES_DB:=llamastack}
         user: ${env.POSTGRES_USER:=llamastack}
         password: ${env.POSTGRES_PASSWORD:=llamastack}
+  safety:
+  - provider_id: llama-guard
+    provider_type: inline::llama-guard
+    config:
+      excluded_categories: []
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
@@ -95,6 +101,8 @@ models:
 - model_id: ${env.INFERENCE_MODEL}
   provider_id: vllm-inference
   model_type: llm
+shields:
+- shield_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}
 vector_dbs: []
 datasets: []
 scoring_fns: []