fix llama stack build for together & llama stack build from templates (…

…#479)

# What does this PR do?

- Fix issue w/ llama stack build using together template
<img width="669" alt="image"
src="https://github.com/user-attachments/assets/1cbef052-d902-40b9-98f8-37efb494d117">

- For builds from templates, copy over the
`templates/<template-name>/run.yaml` file to the
`~/.llama/distributions/<name>/<name>-run.yaml` instead of re-building
run config.


## Test Plan

```
$ llama stack build --template together --image-type conda
..
Build spec configuration saved at /opt/anaconda3/envs/llamastack-together/together-build.yaml
Build Successful! Next steps:
   1. Set the environment variables: LLAMASTACK_PORT, TOGETHER_API_KEY
   2. `llama stack run /Users/xiyan/.llama/distributions/llamastack-together/together-run.yaml`
```

```
$ llama stack run /Users/xiyan/.llama/distributions/llamastack-together/together-run.yaml
```

```
$ llama-stack-client models list
$ pytest -v -s -m remote agents/test_agents.py --env REMOTE_STACK_URL=http://localhost:5000 --inference-model meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
```
<img width="764" alt="image"
src="https://github.com/user-attachments/assets/b805b6c5-a316-4561-8fe3-24fc3b1f8b80">


## Sources

Please link relevant resources if necessary.


## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.

llama_stack/cli/stack/build.py

@@ -8,10 +8,14 @@
 
 from llama_stack.cli.subcommand import Subcommand
 from llama_stack.distribution.datatypes import *  # noqa: F403
+import importlib
 import os
+import shutil
 from functools import lru_cache
 from pathlib import Path
 
+import pkg_resources
+
 from llama_stack.distribution.distribution import get_provider_registry
 from llama_stack.distribution.utils.dynamic import instantiate_class_type
 
@@ -99,7 +103,9 @@ def _run_stack_build_command(self, args: argparse.Namespace) -> None:
                         self.parser.error(
                             f"Please specify a image-type (docker | conda) for {args.template}"
                         )
-                    self._run_stack_build_command_from_build_config(build_config)
+                    self._run_stack_build_command_from_build_config(
+                        build_config, template_name=args.template
+                    )
                     return
 
             self.parser.error(
@@ -248,12 +254,13 @@ def _generate_run_config(self, build_config: BuildConfig, build_dir: Path) -> No
         )
 
     def _run_stack_build_command_from_build_config(
-        self, build_config: BuildConfig
+        self, build_config: BuildConfig, template_name: Optional[str] = None
     ) -> None:
         import json
         import os
 
         import yaml
+        from termcolor import cprint
 
         from llama_stack.distribution.build import build_image
         from llama_stack.distribution.utils.config_dirs import DISTRIBS_BASE_DIR
@@ -271,7 +278,29 @@ def _run_stack_build_command_from_build_config(
         if return_code != 0:
             return
 
-        self._generate_run_config(build_config, build_dir)
+        if template_name:
+            # copy run.yaml from template to build_dir instead of generating it again
+            template_path = pkg_resources.resource_filename(
+                "llama_stack", f"templates/{template_name}/run.yaml"
+            )
+            os.makedirs(build_dir, exist_ok=True)
+            run_config_file = build_dir / f"{build_config.name}-run.yaml"
+            shutil.copy(template_path, run_config_file)
+            module_name = f"llama_stack.templates.{template_name}"
+            module = importlib.import_module(module_name)
+            distribution_template = module.get_distribution_template()
+            cprint("Build Successful! Next steps: ", color="green")
+            env_vars = ", ".join(distribution_template.run_config_env_vars.keys())
+            cprint(
+                f"   1. Set the environment variables: {env_vars}",
+                color="green",
+            )
+            cprint(
+                f"   2. `llama stack run {run_config_file}`",
+                color="green",
+            )
+        else:
+            self._generate_run_config(build_config, build_dir)
 
     def _run_template_list_cmd(self, args: argparse.Namespace) -> None:
         import json

llama_stack/providers/remote/inference/together/config.py

@@ -22,7 +22,7 @@ class TogetherImplConfig(BaseModel):
     )
 
     @classmethod
-    def sample_run_config(cls) -> Dict[str, Any]:
+    def sample_run_config(cls, **kwargs) -> Dict[str, Any]:
         return {
             "url": "https://api.together.xyz/v1",
             "api_key": "${env.TOGETHER_API_KEY}",