merge

llama_stack/templates/vllm-gpu/run.yaml

@@ -47,7 +47,6 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
-      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/vllm-gpu/trace_store.db}
   datasetio:

llama_stack/templates/vllm-gpu/vllm.py

@@ -98,7 +98,7 @@ def get_distribution_template() -> DistributionTemplate:
         },
         run_config_env_vars={
             "LLAMA_STACK_PORT": (
-                "5001",
+                "8321",
                 "Port for the Llama Stack distribution server",
             ),
             "INFERENCE_MODEL": (