fix: replace all instances of --yaml-config with --config (#2196)

# What does this PR do?

start_stack.sh was using --yaml-config which is deprecated.

a bunch of distro docs also mentioned --yaml-config. Replaces all
instances and logic for --yaml-config with --config

resolves #2189

Signed-off-by: Charlie Doern <cdoern@redhat.com>

llama_stack/distribution/server/server.py

@@ -371,9 +371,9 @@ def main(args: argparse.Namespace | None = None):
         args = parser.parse_args()
 
     # Check for deprecated argument usage
-    if "--yaml-config" in sys.argv:
+    if "--config" in sys.argv:
         warnings.warn(
-            "The '--yaml-config' argument is deprecated and will be removed in a future version. Use '--config' instead.",
+            "The '--config' argument is deprecated and will be removed in a future version. Use '--config' instead.",
             DeprecationWarning,
             stacklevel=2,
         )
@@ -391,7 +391,7 @@ def main(args: argparse.Namespace | None = None):
             raise ValueError(f"Template {args.template} does not exist")
         log_line = f"Using template {args.template} config file: {config_file}"
     else:
-        raise ValueError("Either --yaml-config or --template must be provided")
+        raise ValueError("Either --config or --template must be provided")
 
     logger_config = None
     with open(config_file) as fp:

llama_stack/distribution/start_stack.sh

@@ -54,7 +54,7 @@ other_args=""
 # Process remaining arguments
 while [[ $# -gt 0 ]]; do
   case "$1" in
-    --config|--yaml-config)
+    --config)
       if [[ -n "$2" ]]; then
         yaml_config="$2"
         shift 2
@@ -121,7 +121,7 @@ if [[ "$env_type" == "venv" || "$env_type" == "conda" ]]; then
     set -x
 
     if [ -n "$yaml_config" ]; then
-        yaml_config_arg="--yaml-config $yaml_config"
+        yaml_config_arg="--config $yaml_config"
     else
         yaml_config_arg=""
     fi
@@ -181,9 +181,9 @@ elif [[ "$env_type" == "container" ]]; then
 
     # Add yaml config if provided, otherwise use default
     if [ -n "$yaml_config" ]; then
-        cmd="$cmd -v $yaml_config:/app/run.yaml --yaml-config /app/run.yaml"
+        cmd="$cmd -v $yaml_config:/app/run.yaml --config /app/run.yaml"
     else
-        cmd="$cmd --yaml-config /app/run.yaml"
+        cmd="$cmd --config /app/run.yaml"
     fi
 
     # Add any other args

llama_stack/templates/cerebras/doc_template.md

@@ -46,7 +46,7 @@ docker run \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ./run.yaml:/root/my-run.yaml \
   llamastack/distribution-{{ name }} \
-  --yaml-config /root/my-run.yaml \
+  --config /root/my-run.yaml \
   --port $LLAMA_STACK_PORT \
   --env CEREBRAS_API_KEY=$CEREBRAS_API_KEY
 ```

llama_stack/templates/dell/doc_template.md

@@ -143,7 +143,7 @@ docker run \
   -v $HOME/.llama:/root/.llama \
   -v ./llama_stack/templates/tgi/run-with-safety.yaml:/root/my-run.yaml \
   llamastack/distribution-{{ name }} \
-  --yaml-config /root/my-run.yaml \
+  --config /root/my-run.yaml \
   --port $LLAMA_STACK_PORT \
   --env INFERENCE_MODEL=$INFERENCE_MODEL \
   --env DEH_URL=$DEH_URL \

llama_stack/templates/nvidia/doc_template.md

@@ -116,7 +116,7 @@ docker run \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ./run.yaml:/root/my-run.yaml \
   llamastack/distribution-{{ name }} \
-  --yaml-config /root/my-run.yaml \
+  --config /root/my-run.yaml \
   --port $LLAMA_STACK_PORT \
   --env NVIDIA_API_KEY=$NVIDIA_API_KEY
 ```

llama_stack/templates/ollama/doc_template.md

@@ -86,7 +86,7 @@ docker run \
   -v ~/.llama:/root/.llama \
   -v ./llama_stack/templates/ollama/run-with-safety.yaml:/root/my-run.yaml \
   llamastack/distribution-{{ name }} \
-  --yaml-config /root/my-run.yaml \
+  --config /root/my-run.yaml \
   --port $LLAMA_STACK_PORT \
   --env INFERENCE_MODEL=$INFERENCE_MODEL \
   --env SAFETY_MODEL=$SAFETY_MODEL \

llama_stack/templates/remote-vllm/doc_template.md

@@ -220,7 +220,7 @@ docker run \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ./llama_stack/templates/remote-vllm/run.yaml:/root/my-run.yaml \
   llamastack/distribution-{{ name }} \
-  --yaml-config /root/my-run.yaml \
+  --config /root/my-run.yaml \
   --port $LLAMA_STACK_PORT \
   --env INFERENCE_MODEL=$INFERENCE_MODEL \
   --env VLLM_URL=http://host.docker.internal:$INFERENCE_PORT/v1
@@ -242,7 +242,7 @@ docker run \
   -v ~/.llama:/root/.llama \
   -v ./llama_stack/templates/remote-vllm/run-with-safety.yaml:/root/my-run.yaml \
   llamastack/distribution-{{ name }} \
-  --yaml-config /root/my-run.yaml \
+  --config /root/my-run.yaml \
   --port $LLAMA_STACK_PORT \
   --env INFERENCE_MODEL=$INFERENCE_MODEL \
   --env VLLM_URL=http://host.docker.internal:$INFERENCE_PORT/v1 \

llama_stack/templates/tgi/doc_template.md

@@ -105,7 +105,7 @@ docker run \
   -v ~/.llama:/root/.llama \
   -v ./llama_stack/templates/tgi/run-with-safety.yaml:/root/my-run.yaml \
   llamastack/distribution-{{ name }} \
-  --yaml-config /root/my-run.yaml \
+  --config /root/my-run.yaml \
   --port $LLAMA_STACK_PORT \
   --env INFERENCE_MODEL=$INFERENCE_MODEL \
   --env TGI_URL=http://host.docker.internal:$INFERENCE_PORT \

llama_stack/templates/watsonx/doc_template.md

@@ -56,7 +56,7 @@ docker run \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ./run.yaml:/root/my-run.yaml \
   llamastack/distribution-{{ name }} \
-  --yaml-config /root/my-run.yaml \
+  --config /root/my-run.yaml \
   --port $LLAMA_STACK_PORT \
   --env WATSONX_API_KEY=$WATSONX_API_KEY \
   --env WATSONX_PROJECT_ID=$WATSONX_PROJECT_ID \