chore: rename run.yaml to config.yaml

since we only have one config, lets call it config.yaml! this should be treated as the source of truth for starting a stack

change all file names, tests, etc.

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

src/llama_stack/cli/stack/list_stacks.py

@@ -64,14 +64,14 @@ class StackListBuilds(Subcommand):
         for name, (path, source_type) in sorted(distributions.items()):
             row = [name, source_type, str(path)]
             # Check for build and run config files
-            # For built-in distributions, configs are named build.yaml and run.yaml
-            # For custom distributions, configs are named {name}-build.yaml and {name}-run.yaml
+            # For built-in distributions, configs are named build.yaml and config.yaml
+            # For custom distributions, configs are named {name}-build.yaml and {name}-config.yaml
             if source_type == "built-in":
                 build_config = "Yes" if (path / "build.yaml").exists() else "No"
-                run_config = "Yes" if (path / "run.yaml").exists() else "No"
+                run_config = "Yes" if (path / "config.yaml").exists() else "No"
             else:
                 build_config = "Yes" if (path / f"{name}-build.yaml").exists() else "No"
-                run_config = "Yes" if (path / f"{name}-run.yaml").exists() else "No"
+                run_config = "Yes" if (path / f"{name}-config.yaml").exists() else "No"
             row.extend([build_config, run_config])
             rows.append(row)
         print_table(rows, headers, separate_rows=True)

src/llama_stack/cli/stack/utils.py

@@ -57,7 +57,7 @@ def generate_run_config(
     image_name: str,
 ) -> Path:
     """
-    Generate a run.yaml template file for user to edit from a build.yaml file
+    Generate a config.yaml template file for user to edit from a build.yaml file
     """
     apis = list(build_config.distribution_spec.providers.keys())
     distro_dir = DISTRIBS_BASE_DIR / image_name
@@ -123,7 +123,7 @@ def generate_run_config(
             )
             run_config.providers[api].append(p_spec)
 
-    run_config_file = build_dir / f"{image_name}-run.yaml"
+    run_config_file = build_dir / f"{image_name}-config.yaml"
 
     with open(run_config_file, "w") as f:
         to_write = json.loads(run_config.model_dump_json())
@@ -131,7 +131,7 @@ def generate_run_config(
 
     # Only print this message for non-container builds since it will be displayed before the
     # container is built
-    # For non-container builds, the run.yaml is generated at the very end of the build process so it
+    # For non-container builds, the config.yaml is generated at the very end of the build process so it
     # makes sense to display this message
     if build_config.image_type != LlamaStackImageType.CONTAINER.value:
         cprint(f"You can now run your stack with `llama stack run {run_config_file}`", color="green", file=sys.stderr)

src/llama_stack/core/routers/__init__.py

@@ -9,8 +9,8 @@ from typing import Any
 from llama_stack.core.datatypes import (
     AccessRule,
     RoutedProtocol,
+    StackConfig,
 )
-from llama_stack.core.datatypes import StackConfig
 from llama_stack.core.store import DistributionRegistry
 from llama_stack.providers.utils.inference.inference_store import InferenceStore
 from llama_stack_api import Api, RoutingTable

src/llama_stack/core/routing_tables/models.py

@@ -224,7 +224,7 @@ class ModelsRoutingTable(CommonRoutingTableImpl, Models):
         existing_models = await self.get_all_with_type("model")
 
         # we may have an alias for the model registered by the user (or during initialization
-        # from run.yaml) that we need to keep track of
+        # from config.yaml) that we need to keep track of
         model_ids = {}
         for model in existing_models:
             if model.provider_id != provider_id:

src/llama_stack/core/stack.py

@@ -500,7 +500,7 @@ async def refresh_registry_task(impls: dict[Api, Any]):
 
 
 def get_stack_run_config_from_distro(distro: str) -> StackConfig:
-    distro_path = importlib.resources.files("llama_stack") / f"distributions/{distro}/run.yaml"
+    distro_path = importlib.resources.files("llama_stack") / f"distributions/{distro}/config.yaml"
 
     with importlib.resources.as_file(distro_path) as path:
         if not path.exists():

src/llama_stack/distributions/dell/dell.py

@@ -111,7 +111,7 @@ def get_distribution_template() -> DistributionTemplate:
         container_image=None,
         providers=providers,
         run_configs={
-            "run.yaml": RunConfigSettings(
+            "config.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider, embedding_provider],
                     "vector_io": [chromadb_provider],

src/llama_stack/distributions/dell/doc_template.md

@@ -141,14 +141,14 @@ docker run \
   --pull always \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v $HOME/.llama:/root/.llama \
-  -v ./llama_stack/distributions/tgi/run-with-safety.yaml:/root/my-run.yaml \
+  -v ./llama_stack/distributions/tgi/run-with-safety.yaml:/root/my-config.yaml \
   -e INFERENCE_MODEL=$INFERENCE_MODEL \
   -e DEH_URL=$DEH_URL \
   -e SAFETY_MODEL=$SAFETY_MODEL \
   -e DEH_SAFETY_URL=$DEH_SAFETY_URL \
   -e CHROMA_URL=$CHROMA_URL \
   llamastack/distribution-{{ name }} \
-  --config /root/my-run.yaml \
+  --config /root/my-config.yaml \
   --port $LLAMA_STACK_PORT
 ```
 
@@ -157,16 +157,16 @@ docker run \
 You can also run the Docker container with a custom run configuration file by mounting it into the container:
 
 ```bash
-# Set the path to your custom run.yaml file
-CUSTOM_RUN_CONFIG=/path/to/your/custom-run.yaml
+# Set the path to your custom config.yaml file
+CUSTOM_RUN_CONFIG=/path/to/your/custom-config.yaml
 
 docker run -it \
   --pull always \
   --network host \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v $HOME/.llama:/root/.llama \
-  -v $CUSTOM_RUN_CONFIG:/app/custom-run.yaml \
-  -e RUN_CONFIG_PATH=/app/custom-run.yaml \
+  -v $CUSTOM_RUN_CONFIG:/app/custom-config.yaml \
+  -e RUN_CONFIG_PATH=/app/custom-config.yaml \
   -e INFERENCE_MODEL=$INFERENCE_MODEL \
   -e DEH_URL=$DEH_URL \
   -e CHROMA_URL=$CHROMA_URL \

src/llama_stack/distributions/meta-reference-gpu/doc_template.md

@@ -73,8 +73,8 @@ docker run \
 You can also run the Docker container with a custom run configuration file by mounting it into the container:
 
 ```bash
-# Set the path to your custom run.yaml file
-CUSTOM_RUN_CONFIG=/path/to/your/custom-run.yaml
+# Set the path to your custom config.yaml file
+CUSTOM_RUN_CONFIG=/path/to/your/custom-config.yaml
 LLAMA_STACK_PORT=8321
 
 docker run \
@@ -83,8 +83,8 @@ docker run \
   --gpu all \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ~/.llama:/root/.llama \
-  -v $CUSTOM_RUN_CONFIG:/app/custom-run.yaml \
-  -e RUN_CONFIG_PATH=/app/custom-run.yaml \
+  -v $CUSTOM_RUN_CONFIG:/app/custom-config.yaml \
+  -e RUN_CONFIG_PATH=/app/custom-config.yaml \
   llamastack/distribution-{{ name }} \
   --port $LLAMA_STACK_PORT
 ```
@@ -105,7 +105,7 @@ Make sure you have the Llama Stack CLI available.
 ```bash
 llama stack list-deps meta-reference-gpu | xargs -L1 uv pip install
 INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
-llama stack run distributions/{{ name }}/run.yaml \
+llama stack run distributions/{{ name }}/config.yaml \
   --port 8321
 ```
 

src/llama_stack/distributions/meta-reference-gpu/meta_reference.py

@@ -105,7 +105,7 @@ def get_distribution_template() -> DistributionTemplate:
         template_path=Path(__file__).parent / "doc_template.md",
         providers=providers,
         run_configs={
-            "run.yaml": RunConfigSettings(
+            "config.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider, embedding_provider],
                     "vector_io": [vector_io_provider],

src/llama_stack/distributions/nvidia/doc_template.md

@@ -128,8 +128,8 @@ docker run \
 You can also run the Docker container with a custom run configuration file by mounting it into the container:
 
 ```bash
-# Set the path to your custom run.yaml file
-CUSTOM_RUN_CONFIG=/path/to/your/custom-run.yaml
+# Set the path to your custom config.yaml file
+CUSTOM_RUN_CONFIG=/path/to/your/custom-config.yaml
 LLAMA_STACK_PORT=8321
 
 docker run \
@@ -137,8 +137,8 @@ docker run \
   --pull always \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ~/.llama:/root/.llama \
-  -v $CUSTOM_RUN_CONFIG:/app/custom-run.yaml \
-  -e RUN_CONFIG_PATH=/app/custom-run.yaml \
+  -v $CUSTOM_RUN_CONFIG:/app/custom-config.yaml \
+  -e RUN_CONFIG_PATH=/app/custom-config.yaml \
   -e NVIDIA_API_KEY=$NVIDIA_API_KEY \
   llamastack/distribution-{{ name }} \
   --port $LLAMA_STACK_PORT
@@ -162,7 +162,7 @@ INFERENCE_MODEL=meta-llama/Llama-3.1-8B-Instruct
 llama stack list-deps nvidia | xargs -L1 uv pip install
 NVIDIA_API_KEY=$NVIDIA_API_KEY \
 INFERENCE_MODEL=$INFERENCE_MODEL \
-llama stack run ./run.yaml \
+llama stack run ./config.yaml \
   --port 8321
 ```
 

src/llama_stack/distributions/nvidia/nvidia.py

@@ -81,7 +81,7 @@ def get_distribution_template(name: str = "nvidia") -> DistributionTemplate:
         template_path=Path(__file__).parent / "doc_template.md",
         providers=providers,
         run_configs={
-            "run.yaml": RunConfigSettings(
+            "config.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider],
                     "datasetio": [datasetio_provider],

src/llama_stack/distributions/oci/oci.py

@@ -74,7 +74,7 @@ def get_distribution_template(name: str = "oci") -> DistributionTemplate:
         template_path=Path(__file__).parent / "doc_template.md",
         providers=providers,
         run_configs={
-            "run.yaml": RunConfigSettings(
+            "config.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider],
                     "vector_io": [vector_io_provider],

src/llama_stack/distributions/open-benchmark/open_benchmark.py

@@ -261,7 +261,7 @@ def get_distribution_template() -> DistributionTemplate:
         providers=providers,
         available_models_by_provider=available_models,
         run_configs={
-            "run.yaml": RunConfigSettings(
+            "config.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": inference_providers,
                     "vector_io": vector_io_providers,

src/llama_stack/distributions/starter/starter.py

@@ -276,7 +276,7 @@ def get_distribution_template(name: str = "starter") -> DistributionTemplate:
         template_path=None,
         providers=providers,
         run_configs={
-            "run.yaml": base_run_settings,
+            "config.yaml": base_run_settings,
             "run-with-postgres-store.yaml": postgres_run_settings,
         },
         run_config_env_vars={

src/llama_stack/distributions/watsonx/watsonx.py

@@ -69,7 +69,7 @@ def get_distribution_template(name: str = "watsonx") -> DistributionTemplate:
         template_path=None,
         providers=providers,
         run_configs={
-            "run.yaml": RunConfigSettings(
+            "config.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider],
                     "files": [files_provider],

src/llama_stack/log.py

@@ -92,10 +92,10 @@ def config_to_category_levels(category: str, level: str):
 
 def parse_yaml_config(yaml_config: LoggingConfig) -> dict[str, int]:
     """
-    Helper function to parse a yaml logging configuration found in the run.yaml
+    Helper function to parse a yaml logging configuration found in the config.yaml
 
     Parameters:
-        yaml_config (Logging): the logger config object found in the run.yaml
+        yaml_config (Logging): the logger config object found in the config.yaml
 
     Returns:
         Dict[str, int]: A dictionary mapping categories to their log levels.

src/llama_stack/providers/inline/inference/meta_reference/config.py

@@ -16,7 +16,7 @@ class MetaReferenceInferenceConfig(BaseModel):
     # this is a placeholder to indicate inference model id
     # the actual inference model id is dtermined by the moddel id in the request
     # Note: you need to register the model before using it for inference
-    # models in the resouce list in the run.yaml config will be registered automatically
+    # models in the resouce list in the config.yaml config will be registered automatically
     model: str | None = None
     torch_seed: int | None = None
     max_seq_len: int = 4096

src/llama_stack/providers/remote/inference/tgi/tgi.py

@@ -51,7 +51,9 @@ class _HfAdapter(OpenAIMixin):
 class TGIAdapter(_HfAdapter):
     async def initialize(self, config: TGIImplConfig) -> None:
         if not config.base_url:
-            raise ValueError("You must provide a URL in run.yaml (or via the TGI_URL environment variable) to use TGI.")
+            raise ValueError(
+                "You must provide a URL in config.yaml (or via the TGI_URL environment variable) to use TGI."
+            )
         log.info(f"Initializing TGI client with url={config.base_url}")
         # Extract base URL without /v1 for HF client initialization
         base_url_str = str(config.base_url).rstrip("/")

src/llama_stack/providers/remote/inference/vllm/vllm.py

@@ -46,7 +46,7 @@ class VLLMInferenceAdapter(OpenAIMixin):
     async def initialize(self) -> None:
         if not self.config.base_url:
             raise ValueError(
-                "You must provide a URL in run.yaml (or via the VLLM_URL environment variable) to use vLLM."
+                "You must provide a URL in config.yaml (or via the VLLM_URL environment variable) to use vLLM."
             )
 
     async def health(self) -> HealthResponse: