merge

llama_stack/templates/meta-reference-quantized-gpu/doc_template.md

@@ -67,9 +67,10 @@ You can do this via Conda (build code) or Docker which has a pre-built image.
 This method allows you to get started quickly without having to build the distribution code.
 
 ```bash
-LLAMA_STACK_PORT=5001
+LLAMA_STACK_PORT=8321
 docker run \
   -it \
+  --pull always \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ~/.llama:/root/.llama \
   llamastack/distribution-{{ name }} \
@@ -82,6 +83,7 @@ If you are using Llama Stack Safety / Shield APIs, use:
 ```bash
 docker run \
   -it \
+  --pull always \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ~/.llama:/root/.llama \
   llamastack/distribution-{{ name }} \

llama_stack/templates/meta-reference-quantized-gpu/meta_reference.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": (

llama_stack/templates/meta-reference-quantized-gpu/run.yaml

@@ -46,7 +46,6 @@ 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/meta-reference-quantized-gpu/trace_store.db}
   datasetio: