chore: refactor server.main

# What does this PR do?
Refactor main to split out the app construction so that we can use `uvicorn --workers` to enable multi-process stack.


## Test Plan
CI

> uv run --with llama-stack python -m llama_stack.core.server.server benchmarking/k8s-benchmark/stack_run_config.yaml

works.

> LLAMA_STACK_CONFIG=benchmarking/k8s-benchmark/stack_run_config.yaml uv run uvicorn llama_stack.core.server.server:create_app --port 8321 --workers 4

works.

benchmarking/k8s-benchmark/apply.sh

@@ -17,11 +17,8 @@ export POSTGRES_PASSWORD=llamastack
 export INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
 export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
 
-export MOCK_INFERENCE_MODEL=mock-inference
-
-export MOCK_INFERENCE_URL=openai-mock-service:8080
-
 export BENCHMARK_INFERENCE_MODEL=$INFERENCE_MODEL
+export LLAMA_STACK_WORKERS=4
 
 set -euo pipefail
 set -x

benchmarking/k8s-benchmark/stack-configmap.yaml

@@ -5,6 +5,7 @@ data:
     image_name: kubernetes-benchmark-demo
     apis:
     - agents
+    - files
     - inference
     - files
     - safety
@@ -23,6 +24,14 @@ data:
       - provider_id: sentence-transformers
         provider_type: inline::sentence-transformers
         config: {}
+      files:
+      - provider_id: meta-reference-files
+        provider_type: inline::localfs
+        config:
+          storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter/files}
+          metadata_store:
+            type: sqlite
+            db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/files_metadata.db
       vector_io:
       - provider_id: ${env.ENABLE_CHROMADB:+chromadb}
         provider_type: remote::chromadb

benchmarking/k8s-benchmark/stack-k8s.yaml.template

@@ -52,9 +52,20 @@ spec:
           value: http://vllm-server-safety.default.svc.cluster.local:8001/v1
         - name: VLLM_TLS_VERIFY
           value: "false"
-        command: ["python", "-m", "llama_stack.core.server.server", "/etc/config/stack_run_config.yaml", "--port", "8323"]
+        - name: LLAMA_STACK_LOGGING
+          value: "all=WARNING"
+        - name: LLAMA_STACK_CONFIG
+          value: "/etc/config/stack_run_config.yaml"
+        - name: LLAMA_STACK_WORKERS
+          value: "${LLAMA_STACK_WORKERS}"
+        command: ["uvicorn", "llama_stack.core.server.server:create_app", "--host", "0.0.0.0", "--port", "8323", "--workers", "$LLAMA_STACK_WORKERS", "--factory"]
         ports:
           - containerPort: 8323
+        resources:
+          requests:
+            cpu: "${LLAMA_STACK_WORKERS}"
+          limits:
+            cpu: "${LLAMA_STACK_WORKERS}"
         volumeMounts:
           - name: llama-storage
             mountPath: /root/.llama