Fix issue when generating vLLM distros

Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>

llama_stack/templates/remote-vllm/run-with-safety.yaml

@@ -1,5 +1,6 @@
 version: '2'
 image_name: remote-vllm
+docker_image: null
 conda_env: remote-vllm
 apis:
 - agents
@@ -7,7 +8,6 @@ apis:
 - memory
 - safety
 - telemetry
-- tool_runtime
 providers:
   inference:
   - provider_id: vllm-inference
@@ -52,50 +52,33 @@ providers:
       service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/remote-vllm/trace_store.db}
-  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/remote-vllm}/registry.db
 models:
 - metadata: {}
   model_id: ${env.INFERENCE_MODEL}
   provider_id: vllm-inference
+  provider_model_id: null
   model_type: llm
 - metadata: {}
   model_id: ${env.SAFETY_MODEL}
   provider_id: vllm-safety
+  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:
-- shield_id: ${env.SAFETY_MODEL}
+- params: null
+  shield_id: ${env.SAFETY_MODEL}
+  provider_id: null
+  provider_shield_id: null
 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/remote-vllm/run.yaml

@@ -1,5 +1,6 @@
 version: '2'
 image_name: remote-vllm
+docker_image: null
 conda_env: remote-vllm
 apis:
 - agents
@@ -7,7 +8,6 @@ apis:
 - memory
 - safety
 - telemetry
-- tool_runtime
 providers:
   inference:
   - provider_id: vllm-inference
@@ -46,39 +46,24 @@ providers:
       service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/remote-vllm/trace_store.db}
-  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/remote-vllm}/registry.db
 models:
 - metadata: {}
   model_id: ${env.INFERENCE_MODEL}
   provider_id: vllm-inference
+  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: []

llama_stack/templates/remote-vllm/vllm.py

@@ -134,7 +134,7 @@ def get_distribution_template() -> DistributionTemplate:
                 "Inference model loaded into the vLLM server",
             ),
             "VLLM_URL": (
-                "http://host.docker.internal:5100}/v1",
+                "http://host.docker.internal:5100/v1",
                 "URL of the vLLM server with the main inference model",
             ),
             "MAX_TOKENS": (