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>

docs/source/distributions/kubernetes_deployment.md

@@ -172,7 +172,7 @@ spec:
       - name: llama-stack
         image: localhost/llama-stack-run-k8s:latest
         imagePullPolicy: IfNotPresent
-        command: ["python", "-m", "llama_stack.distribution.server.server", "--yaml-config", "/app/config.yaml"]
+        command: ["python", "-m", "llama_stack.distribution.server.server", "--config", "/app/config.yaml"]
         ports:
           - containerPort: 5000
         volumeMounts:

docs/source/distributions/remote_hosted_distro/watsonx.md

@@ -70,7 +70,7 @@ docker run \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ./run.yaml:/root/my-run.yaml \
   llamastack/distribution-watsonx \
-  --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 \

docs/source/distributions/self_hosted_distro/cerebras.md

@@ -52,7 +52,7 @@ docker run \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ./run.yaml:/root/my-run.yaml \
   llamastack/distribution-cerebras \
-  --yaml-config /root/my-run.yaml \
+  --config /root/my-run.yaml \
   --port $LLAMA_STACK_PORT \
   --env CEREBRAS_API_KEY=$CEREBRAS_API_KEY
 ```

docs/source/distributions/self_hosted_distro/dell.md

@@ -155,7 +155,7 @@ docker run \
   -v $HOME/.llama:/root/.llama \
   -v ./llama_stack/templates/tgi/run-with-safety.yaml:/root/my-run.yaml \
   llamastack/distribution-dell \
-  --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 \

docs/source/distributions/self_hosted_distro/nvidia.md

@@ -143,7 +143,7 @@ docker run \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ./run.yaml:/root/my-run.yaml \
   llamastack/distribution-nvidia \
-  --yaml-config /root/my-run.yaml \
+  --config /root/my-run.yaml \
   --port $LLAMA_STACK_PORT \
   --env NVIDIA_API_KEY=$NVIDIA_API_KEY
 ```

docs/source/distributions/self_hosted_distro/ollama.md

@@ -97,7 +97,7 @@ docker run \
   -v ~/.llama:/root/.llama \
   -v ./llama_stack/templates/ollama/run-with-safety.yaml:/root/my-run.yaml \
   llamastack/distribution-ollama \
-  --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 \

docs/source/distributions/self_hosted_distro/remote-vllm.md

@@ -233,7 +233,7 @@ docker run \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ./llama_stack/templates/remote-vllm/run.yaml:/root/my-run.yaml \
   llamastack/distribution-remote-vllm \
-  --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
@@ -255,7 +255,7 @@ docker run \
   -v ~/.llama:/root/.llama \
   -v ./llama_stack/templates/remote-vllm/run-with-safety.yaml:/root/my-run.yaml \
   llamastack/distribution-remote-vllm \
-  --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 \

docs/source/distributions/self_hosted_distro/tgi.md

@@ -117,7 +117,7 @@ docker run \
   -v ~/.llama:/root/.llama \
   -v ./llama_stack/templates/tgi/run-with-safety.yaml:/root/my-run.yaml \
   llamastack/distribution-tgi \
-  --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 \