all templates to include toolgroups and tool runtime

llama_stack/templates/vllm-gpu/build.yaml

@@ -2,7 +2,6 @@ version: '2'
 name: vllm-gpu
 distribution_spec:
   description: Use a built-in vLLM engine for running LLM inference
-  docker_image: null
   providers:
     inference:
     - inline::vllm
@@ -25,4 +24,9 @@ distribution_spec:
     - inline::basic
     - inline::llm-as-judge
     - inline::braintrust
+    tool_runtime:
+    - remote::brave-search
+    - remote::tavily-search
+    - inline::code-interpreter
+    - inline::memory-runtime
 image_type: conda

llama_stack/templates/vllm-gpu/run.yaml

@@ -1,6 +1,5 @@
 version: '2'
 image_name: vllm-gpu
-docker_image: null
 conda_env: vllm-gpu
 apis:
 - agents
@@ -11,6 +10,7 @@ apis:
 - safety
 - scoring
 - telemetry
+- tool_runtime
 providers:
   inference:
   - provider_id: vllm
@@ -73,24 +73,45 @@ providers:
     provider_type: inline::braintrust
     config:
       openai_api_key: ${env.OPENAI_API_KEY:}
+  tool_runtime:
+  - provider_id: brave-search
+    provider_type: remote::brave-search
+    config:
+      api_key: ${env.BRAVE_SEARCH_API_KEY:}
+      max_results: 3
+  - provider_id: tavily-search
+    provider_type: remote::tavily-search
+    config:
+      api_key: ${env.TAVILY_SEARCH_API_KEY:}
+      max_results: 3
+  - provider_id: code-interpreter
+    provider_type: inline::code-interpreter
+    config: {}
+  - provider_id: memory-runtime
+    provider_type: inline::memory-runtime
+    config: {}
 metadata_store:
-  namespace: null
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/vllm-gpu}/registry.db
 models:
 - metadata: {}
   model_id: ${env.INFERENCE_MODEL}
   provider_id: vllm
-  provider_model_id: null
   model_type: llm
 - metadata:
     embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
   provider_id: sentence-transformers
-  provider_model_id: null
   model_type: embedding
 shields: []
 memory_banks: []
 datasets: []
 scoring_fns: []
 eval_tasks: []
+tool_groups:
+- toolgroup_id: builtin::websearch
+  provider_id: tavily-search
+- toolgroup_id: builtin::memory
+  provider_id: memory-runtime
+- toolgroup_id: builtin::code_interpreter
+  provider_id: code-interpreter

llama_stack/templates/vllm-gpu/vllm.py

@@ -11,7 +11,11 @@ from llama_stack.providers.inline.inference.sentence_transformers import (
 )
 from llama_stack.providers.inline.inference.vllm import VLLMConfig
 from llama_stack.providers.inline.memory.faiss.config import FaissImplConfig
-from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
+from llama_stack.templates.template import (
+    DistributionTemplate,
+    RunConfigSettings,
+    ToolGroupInput,
+)
 
 
 def get_distribution_template() -> DistributionTemplate:
@@ -24,7 +28,14 @@ def get_distribution_template() -> DistributionTemplate:
         "eval": ["inline::meta-reference"],
         "datasetio": ["remote::huggingface", "inline::localfs"],
         "scoring": ["inline::basic", "inline::llm-as-judge", "inline::braintrust"],
+        "tool_runtime": [
+            "remote::brave-search",
+            "remote::tavily-search",
+            "inline::code-interpreter",
+            "inline::memory-runtime",
+        ],
     }
+
     name = "vllm-gpu"
     inference_provider = Provider(
         provider_id="vllm",
@@ -54,6 +65,20 @@ def get_distribution_template() -> DistributionTemplate:
             "embedding_dimension": 384,
         },
     )
+    default_tool_groups = [
+        ToolGroupInput(
+            toolgroup_id="builtin::websearch",
+            provider_id="tavily-search",
+        ),
+        ToolGroupInput(
+            toolgroup_id="builtin::memory",
+            provider_id="memory-runtime",
+        ),
+        ToolGroupInput(
+            toolgroup_id="builtin::code_interpreter",
+            provider_id="code-interpreter",
+        ),
+    ]
 
     return DistributionTemplate(
         name=name,
@@ -70,6 +95,7 @@ def get_distribution_template() -> DistributionTemplate:
                     "memory": [memory_provider],
                 },
                 default_models=[inference_model, embedding_model],
+                default_tool_groups=default_tool_groups,
             ),
         },
         run_config_env_vars={