Merge branch 'main' into nvidia-e2e-notebook

2025-07-23 21:04:29 +00:00 · 2025-06-06 11:11:53 -04:00 · 2025-06-06 11:11:53 -04:00 · 1a492ad0cc
commit 1a492ad0cc
parent 6a004e99ed 0d0b8d2be1
200 changed files with 8714 additions and 3175 deletions
--- a/llama_stack/templates/bedrock/build.yaml
+++ b/llama_stack/templates/bedrock/build.yaml
@ -30,4 +30,5 @@ distribution_spec:
    - remote::model-context-protocol
 image_type: conda
 additional_pip_packages:
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/bedrock/run.yaml
+++ b/llama_stack/templates/bedrock/run.yaml
@ -42,7 +42,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/bedrock}/trace_store.db
  eval:
--- a/llama_stack/templates/cerebras/build.yaml
+++ b/llama_stack/templates/cerebras/build.yaml
@ -30,4 +30,5 @@ distribution_spec:
    - inline::rag-runtime
 image_type: conda
 additional_pip_packages:
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/cerebras/run.yaml
+++ b/llama_stack/templates/cerebras/run.yaml
@ -82,7 +82,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/cerebras}/trace_store.db
  tool_runtime:
--- a/llama_stack/templates/ci-tests/build.yaml
+++ b/llama_stack/templates/ci-tests/build.yaml
@ -31,4 +31,5 @@ distribution_spec:
    - remote::model-context-protocol
 image_type: conda
 additional_pip_packages:
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/ci-tests/run.yaml
+++ b/llama_stack/templates/ci-tests/run.yaml
@ -45,7 +45,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ci-tests}/trace_store.db
  eval:
--- a/llama_stack/templates/dell/build.yaml
+++ b/llama_stack/templates/dell/build.yaml
@ -31,5 +31,5 @@ distribution_spec:
    - inline::rag-runtime
 image_type: conda
 additional_pip_packages:
- sqlalchemy[asyncio]
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/dell/run-with-safety.yaml
+++ b/llama_stack/templates/dell/run-with-safety.yaml
@ -48,7 +48,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/trace_store.db
  eval:
--- a/llama_stack/templates/dell/run.yaml
+++ b/llama_stack/templates/dell/run.yaml
@ -44,7 +44,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/trace_store.db
  eval:
--- a/llama_stack/templates/fireworks/build.yaml
+++ b/llama_stack/templates/fireworks/build.yaml
@ -24,6 +24,8 @@ distribution_spec:
    - inline::basic
    - inline::llm-as-judge
    - inline::braintrust
+    files:
+    - inline::localfs
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
@ -32,5 +34,5 @@ distribution_spec:
    - remote::model-context-protocol
 image_type: conda
 additional_pip_packages:
- sqlalchemy[asyncio]
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/fireworks/fireworks.py
+++ b/llama_stack/templates/fireworks/fireworks.py
@ -13,6 +13,7 @@ from llama_stack.distribution.datatypes import (
    ShieldInput,
    ToolGroupInput,
 )
+from llama_stack.providers.inline.files.localfs.config import LocalfsFilesImplConfig
 from llama_stack.providers.inline.inference.sentence_transformers import (
    SentenceTransformersInferenceConfig,
 )
@ -36,6 +37,7 @@ def get_distribution_template() -> DistributionTemplate:
        "eval": ["inline::meta-reference"],
        "datasetio": ["remote::huggingface", "inline::localfs"],
        "scoring": ["inline::basic", "inline::llm-as-judge", "inline::braintrust"],
+        "files": ["inline::localfs"],
        "tool_runtime": [
            "remote::brave-search",
            "remote::tavily-search",
@ -62,6 +64,11 @@ def get_distribution_template() -> DistributionTemplate:
        provider_type="inline::faiss",
        config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
    )
+    files_provider = Provider(
+        provider_id="meta-reference-files",
+        provider_type="inline::localfs",
+        config=LocalfsFilesImplConfig.sample_run_config(f"~/.llama/distributions/{name}"),
+    )

    available_models = {
        "fireworks": MODEL_ENTRIES,
@ -104,6 +111,7 @@ def get_distribution_template() -> DistributionTemplate:
                provider_overrides={
                    "inference": [inference_provider, embedding_provider],
                    "vector_io": [vector_io_provider],
+                    "files": [files_provider],
                },
                default_models=default_models + [embedding_model],
                default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
@ -116,6 +124,7 @@ def get_distribution_template() -> DistributionTemplate:
                        embedding_provider,
                    ],
                    "vector_io": [vector_io_provider],
+                    "files": [files_provider],
                    "safety": [
                        Provider(
                            provider_id="llama-guard",
--- a/llama_stack/templates/fireworks/run-with-safety.yaml
+++ b/llama_stack/templates/fireworks/run-with-safety.yaml
@ -4,6 +4,7 @@ apis:
 - agents
 - datasetio
 - eval
+- files
 - inference
 - safety
 - scoring
@ -53,7 +54,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/trace_store.db
  eval:
@ -90,6 +91,14 @@ providers:
    provider_type: inline::braintrust
    config:
      openai_api_key: ${env.OPENAI_API_KEY:}
+  files:
+  - provider_id: meta-reference-files
+    provider_type: inline::localfs
+    config:
+      storage_dir: ${env.FILES_STORAGE_DIR:~/.llama/distributions/fireworks/files}
+      metadata_store:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/files_metadata.db
  tool_runtime:
  - provider_id: brave-search
    provider_type: remote::brave-search
--- a/llama_stack/templates/fireworks/run.yaml
+++ b/llama_stack/templates/fireworks/run.yaml
@ -4,6 +4,7 @@ apis:
 - agents
 - datasetio
 - eval
+- files
 - inference
 - safety
 - scoring
@ -48,7 +49,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/trace_store.db
  eval:
@ -85,6 +86,14 @@ providers:
    provider_type: inline::braintrust
    config:
      openai_api_key: ${env.OPENAI_API_KEY:}
+  files:
+  - provider_id: meta-reference-files
+    provider_type: inline::localfs
+    config:
+      storage_dir: ${env.FILES_STORAGE_DIR:~/.llama/distributions/fireworks/files}
+      metadata_store:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/files_metadata.db
  tool_runtime:
  - provider_id: brave-search
    provider_type: remote::brave-search
--- a/llama_stack/templates/groq/build.yaml
+++ b/llama_stack/templates/groq/build.yaml
@ -27,4 +27,5 @@ distribution_spec:
    - inline::rag-runtime
 image_type: conda
 additional_pip_packages:
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/groq/run.yaml
+++ b/llama_stack/templates/groq/run.yaml
@ -48,7 +48,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/trace_store.db
  eval:
@ -112,7 +112,7 @@ models:
  provider_model_id: groq/llama3-8b-8192
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.1-8B-Instruct
+  model_id: groq/meta-llama/Llama-3.1-8B-Instruct
  provider_id: groq
  provider_model_id: groq/llama3-8b-8192
  model_type: llm
@ -127,7 +127,7 @@ models:
  provider_model_id: groq/llama3-70b-8192
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3-70B-Instruct
+  model_id: groq/meta-llama/Llama-3-70B-Instruct
  provider_id: groq
  provider_model_id: groq/llama3-70b-8192
  model_type: llm
@ -137,7 +137,7 @@ models:
  provider_model_id: groq/llama-3.3-70b-versatile
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.3-70B-Instruct
+  model_id: groq/meta-llama/Llama-3.3-70B-Instruct
  provider_id: groq
  provider_model_id: groq/llama-3.3-70b-versatile
  model_type: llm
@ -147,7 +147,7 @@ models:
  provider_model_id: groq/llama-3.2-3b-preview
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.2-3B-Instruct
+  model_id: groq/meta-llama/Llama-3.2-3B-Instruct
  provider_id: groq
  provider_model_id: groq/llama-3.2-3b-preview
  model_type: llm
@ -157,7 +157,7 @@ models:
  provider_model_id: groq/llama-4-scout-17b-16e-instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  model_id: groq/meta-llama/Llama-4-Scout-17B-16E-Instruct
  provider_id: groq
  provider_model_id: groq/llama-4-scout-17b-16e-instruct
  model_type: llm
@ -167,7 +167,7 @@ models:
  provider_model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  model_id: groq/meta-llama/Llama-4-Scout-17B-16E-Instruct
  provider_id: groq
  provider_model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
  model_type: llm
@ -177,7 +177,7 @@ models:
  provider_model_id: groq/llama-4-maverick-17b-128e-instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  model_id: groq/meta-llama/Llama-4-Maverick-17B-128E-Instruct
  provider_id: groq
  provider_model_id: groq/llama-4-maverick-17b-128e-instruct
  model_type: llm
@ -187,7 +187,7 @@ models:
  provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  model_id: groq/meta-llama/Llama-4-Maverick-17B-128E-Instruct
  provider_id: groq
  provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
  model_type: llm
--- a/llama_stack/templates/hf-endpoint/build.yaml
+++ b/llama_stack/templates/hf-endpoint/build.yaml
@ -30,5 +30,5 @@ distribution_spec:
    - remote::model-context-protocol
 image_type: conda
 additional_pip_packages:
- sqlalchemy[asyncio]
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/hf-endpoint/run-with-safety.yaml
+++ b/llama_stack/templates/hf-endpoint/run-with-safety.yaml
@ -53,7 +53,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/trace_store.db
  eval:
--- a/llama_stack/templates/hf-endpoint/run.yaml
+++ b/llama_stack/templates/hf-endpoint/run.yaml
@ -48,7 +48,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/trace_store.db
  eval:
--- a/llama_stack/templates/hf-serverless/build.yaml
+++ b/llama_stack/templates/hf-serverless/build.yaml
@ -31,5 +31,5 @@ distribution_spec:
    - remote::model-context-protocol
 image_type: conda
 additional_pip_packages:
- sqlalchemy[asyncio]
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/hf-serverless/run-with-safety.yaml
+++ b/llama_stack/templates/hf-serverless/run-with-safety.yaml
@ -53,7 +53,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/trace_store.db
  eval:
--- a/llama_stack/templates/hf-serverless/run.yaml
+++ b/llama_stack/templates/hf-serverless/run.yaml
@ -48,7 +48,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/trace_store.db
  eval:
--- a/llama_stack/templates/llama_api/build.yaml
+++ b/llama_stack/templates/llama_api/build.yaml
@ -31,4 +31,5 @@ distribution_spec:
    - remote::model-context-protocol
 image_type: conda
 additional_pip_packages:
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/llama_api/run.yaml
+++ b/llama_stack/templates/llama_api/run.yaml
@ -57,7 +57,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/llama_api}/trace_store.db
  eval:
--- a/llama_stack/templates/meta-reference-gpu/build.yaml
+++ b/llama_stack/templates/meta-reference-gpu/build.yaml
@ -30,5 +30,5 @@ distribution_spec:
    - remote::model-context-protocol
 image_type: conda
 additional_pip_packages:
- sqlalchemy[asyncio]
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/meta-reference-gpu/run-with-safety.yaml
+++ b/llama_stack/templates/meta-reference-gpu/run-with-safety.yaml
@ -63,7 +63,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/trace_store.db
  eval:
--- a/llama_stack/templates/meta-reference-gpu/run.yaml
+++ b/llama_stack/templates/meta-reference-gpu/run.yaml
@ -53,7 +53,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/trace_store.db
  eval:
--- a/llama_stack/templates/nvidia/build.yaml
+++ b/llama_stack/templates/nvidia/build.yaml
@ -25,5 +25,5 @@ distribution_spec:
    - inline::rag-runtime
 image_type: conda
 additional_pip_packages:
- sqlalchemy[asyncio]
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/nvidia/run-with-safety.yaml
+++ b/llama_stack/templates/nvidia/run-with-safety.yaml
@ -53,7 +53,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/trace_store.db
  eval:
--- a/llama_stack/templates/nvidia/run.yaml
+++ b/llama_stack/templates/nvidia/run.yaml
@ -48,7 +48,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/trace_store.db
  eval:
--- a/llama_stack/templates/ollama/build.yaml
+++ b/llama_stack/templates/ollama/build.yaml
@ -33,5 +33,5 @@ distribution_spec:
    - remote::wolfram-alpha
 image_type: conda
 additional_pip_packages:
- sqlalchemy[asyncio]
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/ollama/run-with-safety.yaml
+++ b/llama_stack/templates/ollama/run-with-safety.yaml
@ -47,7 +47,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/trace_store.db
  eval:
--- a/llama_stack/templates/ollama/run.yaml
+++ b/llama_stack/templates/ollama/run.yaml
@ -45,7 +45,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/trace_store.db
  eval:
--- a/llama_stack/templates/open-benchmark/build.yaml
+++ b/llama_stack/templates/open-benchmark/build.yaml
@ -34,4 +34,5 @@ distribution_spec:
    - remote::model-context-protocol
 image_type: conda
 additional_pip_packages:
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/open-benchmark/run.yaml
+++ b/llama_stack/templates/open-benchmark/run.yaml
@ -71,7 +71,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open-benchmark}/trace_store.db
  eval:
--- a/llama_stack/templates/passthrough/build.yaml
+++ b/llama_stack/templates/passthrough/build.yaml
@ -32,5 +32,5 @@ distribution_spec:
    - remote::model-context-protocol
 image_type: conda
 additional_pip_packages:
- sqlalchemy[asyncio]
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/passthrough/run-with-safety.yaml
+++ b/llama_stack/templates/passthrough/run-with-safety.yaml
@ -53,7 +53,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/passthrough}/trace_store.db
  eval:
--- a/llama_stack/templates/passthrough/run.yaml
+++ b/llama_stack/templates/passthrough/run.yaml
@ -48,7 +48,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/passthrough}/trace_store.db
  eval:
--- a/llama_stack/templates/postgres-demo/init.py
+++ b/llama_stack/templates/postgres-demo/init.py
@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.

-from .verification import get_distribution_template  # noqa: F401
+from .postgres_demo import get_distribution_template  # noqa: F401
--- a/llama_stack/templates/postgres-demo/build.yaml
+++ b/llama_stack/templates/postgres-demo/build.yaml
@ -0,0 +1,25 @@
+version: '2'
+distribution_spec:
+  description: Quick start template for running Llama Stack with several popular providers
+  providers:
+    inference:
+    - remote::vllm
+    - inline::sentence-transformers
+    vector_io:
+    - remote::chromadb
+    safety:
+    - inline::llama-guard
+    agents:
+    - inline::meta-reference
+    telemetry:
+    - inline::meta-reference
+    tool_runtime:
+    - remote::brave-search
+    - remote::tavily-search
+    - inline::rag-runtime
+    - remote::model-context-protocol
+image_type: conda
+additional_pip_packages:
+- asyncpg
+- psycopg2-binary
+- sqlalchemy[asyncio]
--- a/llama_stack/templates/postgres-demo/postgres_demo.py
+++ b/llama_stack/templates/postgres-demo/postgres_demo.py
@ -0,0 +1,137 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+
+from llama_stack.apis.models.models import ModelType
+from llama_stack.distribution.datatypes import (
+    ModelInput,
+    Provider,
+    ShieldInput,
+    ToolGroupInput,
+)
+from llama_stack.providers.inline.inference.sentence_transformers import SentenceTransformersInferenceConfig
+from llama_stack.providers.remote.inference.vllm import VLLMInferenceAdapterConfig
+from llama_stack.providers.remote.vector_io.chroma.config import ChromaVectorIOConfig
+from llama_stack.providers.utils.kvstore.config import PostgresKVStoreConfig
+from llama_stack.providers.utils.sqlstore.sqlstore import PostgresSqlStoreConfig
+from llama_stack.templates.template import (
+    DistributionTemplate,
+    RunConfigSettings,
+)
+
+
+def get_distribution_template() -> DistributionTemplate:
+    inference_providers = [
+        Provider(
+            provider_id="vllm-inference",
+            provider_type="remote::vllm",
+            config=VLLMInferenceAdapterConfig.sample_run_config(
+                url="${env.VLLM_URL:http://localhost:8000/v1}",
+            ),
+        ),
+    ]
+    providers = {
+        "inference": ([p.provider_type for p in inference_providers] + ["inline::sentence-transformers"]),
+        "vector_io": ["remote::chromadb"],
+        "safety": ["inline::llama-guard"],
+        "agents": ["inline::meta-reference"],
+        "telemetry": ["inline::meta-reference"],
+        "tool_runtime": [
+            "remote::brave-search",
+            "remote::tavily-search",
+            "inline::rag-runtime",
+            "remote::model-context-protocol",
+        ],
+    }
+    name = "postgres-demo"
+
+    vector_io_providers = [
+        Provider(
+            provider_id="${env.ENABLE_CHROMADB+chromadb}",
+            provider_type="remote::chromadb",
+            config=ChromaVectorIOConfig.sample_run_config(url="${env.CHROMADB_URL:}"),
+        ),
+    ]
+    default_tool_groups = [
+        ToolGroupInput(
+            toolgroup_id="builtin::websearch",
+            provider_id="tavily-search",
+        ),
+        ToolGroupInput(
+            toolgroup_id="builtin::rag",
+            provider_id="rag-runtime",
+        ),
+    ]
+
+    default_models = [
+        ModelInput(
+            model_id="${env.INFERENCE_MODEL}",
+            provider_id="vllm-inference",
+        )
+    ]
+    embedding_provider = Provider(
+        provider_id="sentence-transformers",
+        provider_type="inline::sentence-transformers",
+        config=SentenceTransformersInferenceConfig.sample_run_config(),
+    )
+    embedding_model = ModelInput(
+        model_id="all-MiniLM-L6-v2",
+        provider_id=embedding_provider.provider_id,
+        model_type=ModelType.embedding,
+        metadata={
+            "embedding_dimension": 384,
+        },
+    )
+    postgres_config = PostgresSqlStoreConfig.sample_run_config()
+    return DistributionTemplate(
+        name=name,
+        distro_type="self_hosted",
+        description="Quick start template for running Llama Stack with several popular providers",
+        container_image=None,
+        template_path=None,
+        providers=providers,
+        available_models_by_provider={},
+        run_configs={
+            "run.yaml": RunConfigSettings(
+                provider_overrides={
+                    "inference": inference_providers + [embedding_provider],
+                    "vector_io": vector_io_providers,
+                    "agents": [
+                        Provider(
+                            provider_id="meta-reference",
+                            provider_type="inline::meta-reference",
+                            config=dict(
+                                persistence_store=postgres_config,
+                                responses_store=postgres_config,
+                            ),
+                        )
+                    ],
+                    "telemetry": [
+                        Provider(
+                            provider_id="meta-reference",
+                            provider_type="inline::meta-reference",
+                            config=dict(
+                                service_name="${env.OTEL_SERVICE_NAME:}",
+                                sinks="${env.TELEMETRY_SINKS:console,otel_trace}",
+                                otel_trace_endpoint="${env.OTEL_TRACE_ENDPOINT:http://localhost:4318/v1/traces}",
+                            ),
+                        )
+                    ],
+                },
+                default_models=default_models + [embedding_model],
+                default_tool_groups=default_tool_groups,
+                default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
+                metadata_store=PostgresKVStoreConfig.sample_run_config(),
+                inference_store=postgres_config,
+            ),
+        },
+        run_config_env_vars={
+            "LLAMA_STACK_PORT": (
+                "8321",
+                "Port for the Llama Stack distribution server",
+            ),
+        },
+    )
--- a/llama_stack/templates/postgres-demo/run.yaml
+++ b/llama_stack/templates/postgres-demo/run.yaml
@ -0,0 +1,111 @@
+version: '2'
+image_name: postgres-demo
+apis:
+- agents
+- inference
+- safety
+- telemetry
+- tool_runtime
+- vector_io
+providers:
+  inference:
+  - provider_id: vllm-inference
+    provider_type: remote::vllm
+    config:
+      url: ${env.VLLM_URL:http://localhost:8000/v1}
+      max_tokens: ${env.VLLM_MAX_TOKENS:4096}
+      api_token: ${env.VLLM_API_TOKEN:fake}
+      tls_verify: ${env.VLLM_TLS_VERIFY:true}
+  - provider_id: sentence-transformers
+    provider_type: inline::sentence-transformers
+    config: {}
+  vector_io:
+  - provider_id: ${env.ENABLE_CHROMADB+chromadb}
+    provider_type: remote::chromadb
+    config:
+      url: ${env.CHROMADB_URL:}
+  safety:
+  - provider_id: llama-guard
+    provider_type: inline::llama-guard
+    config:
+      excluded_categories: []
+  agents:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      persistence_store:
+        type: postgres
+        host: ${env.POSTGRES_HOST:localhost}
+        port: ${env.POSTGRES_PORT:5432}
+        db: ${env.POSTGRES_DB:llamastack}
+        user: ${env.POSTGRES_USER:llamastack}
+        password: ${env.POSTGRES_PASSWORD:llamastack}
+      responses_store:
+        type: postgres
+        host: ${env.POSTGRES_HOST:localhost}
+        port: ${env.POSTGRES_PORT:5432}
+        db: ${env.POSTGRES_DB:llamastack}
+        user: ${env.POSTGRES_USER:llamastack}
+        password: ${env.POSTGRES_PASSWORD:llamastack}
+  telemetry:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:}
+      sinks: ${env.TELEMETRY_SINKS:console,otel_trace}
+      otel_trace_endpoint: ${env.OTEL_TRACE_ENDPOINT:http://localhost:4318/v1/traces}
+  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: rag-runtime
+    provider_type: inline::rag-runtime
+    config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
+metadata_store:
+  type: postgres
+  host: ${env.POSTGRES_HOST:localhost}
+  port: ${env.POSTGRES_PORT:5432}
+  db: ${env.POSTGRES_DB:llamastack}
+  user: ${env.POSTGRES_USER:llamastack}
+  password: ${env.POSTGRES_PASSWORD:llamastack}
+  table_name: ${env.POSTGRES_TABLE_NAME:llamastack_kvstore}
+inference_store:
+  type: postgres
+  host: ${env.POSTGRES_HOST:localhost}
+  port: ${env.POSTGRES_PORT:5432}
+  db: ${env.POSTGRES_DB:llamastack}
+  user: ${env.POSTGRES_USER:llamastack}
+  password: ${env.POSTGRES_PASSWORD:llamastack}
+models:
+- metadata: {}
+  model_id: ${env.INFERENCE_MODEL}
+  provider_id: vllm-inference
+  model_type: llm
+- metadata:
+    embedding_dimension: 384
+  model_id: all-MiniLM-L6-v2
+  provider_id: sentence-transformers
+  model_type: embedding
+shields:
+- shield_id: meta-llama/Llama-Guard-3-8B
+vector_dbs: []
+datasets: []
+scoring_fns: []
+benchmarks: []
+tool_groups:
+- toolgroup_id: builtin::websearch
+  provider_id: tavily-search
+- toolgroup_id: builtin::rag
+  provider_id: rag-runtime
+server:
+  port: 8321
--- a/llama_stack/templates/remote-vllm/build.yaml
+++ b/llama_stack/templates/remote-vllm/build.yaml
@ -32,5 +32,5 @@ distribution_spec:
    - remote::wolfram-alpha
 image_type: conda
 additional_pip_packages:
- sqlalchemy[asyncio]
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/remote-vllm/run-with-safety.yaml
+++ b/llama_stack/templates/remote-vllm/run-with-safety.yaml
@ -91,7 +91,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/trace_store.db
  tool_runtime:
--- a/llama_stack/templates/remote-vllm/run.yaml
+++ b/llama_stack/templates/remote-vllm/run.yaml
@ -84,7 +84,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/trace_store.db
  tool_runtime:
--- a/llama_stack/templates/sambanova/build.yaml
+++ b/llama_stack/templates/sambanova/build.yaml
@ -23,4 +23,5 @@ distribution_spec:
    - remote::wolfram-alpha
 image_type: conda
 additional_pip_packages:
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/sambanova/run.yaml
+++ b/llama_stack/templates/sambanova/run.yaml
@ -58,7 +58,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/sambanova}/trace_store.db
  tool_runtime:
--- a/llama_stack/templates/starter/build.yaml
+++ b/llama_stack/templates/starter/build.yaml
@ -5,10 +5,13 @@ distribution_spec:
    inference:
    - remote::openai
    - remote::fireworks
+    - remote::together
+    - remote::ollama
    - remote::anthropic
    - remote::gemini
    - remote::groq
    - remote::sambanova
+    - remote::vllm
    - inline::sentence-transformers
    vector_io:
    - inline::sqlite-vec
@ -36,4 +39,6 @@ distribution_spec:
    - remote::model-context-protocol
 image_type: conda
 additional_pip_packages:
+- aiosqlite
+- asyncpg
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/starter/run.yaml
+++ b/llama_stack/templates/starter/run.yaml
@ -21,6 +21,15 @@ providers:
    config:
      url: https://api.fireworks.ai/inference/v1
      api_key: ${env.FIREWORKS_API_KEY:}
+  - provider_id: together
+    provider_type: remote::together
+    config:
+      url: https://api.together.xyz/v1
+      api_key: ${env.TOGETHER_API_KEY:}
+  - provider_id: ollama
+    provider_type: remote::ollama
+    config:
+      url: ${env.OLLAMA_URL:http://localhost:11434}
  - provider_id: anthropic
    provider_type: remote::anthropic
    config:
@ -39,6 +48,13 @@ providers:
    config:
      url: https://api.sambanova.ai/v1
      api_key: ${env.SAMBANOVA_API_KEY:}
+  - provider_id: vllm
+    provider_type: remote::vllm
+    config:
+      url: ${env.VLLM_URL:http://localhost:8000/v1}
+      max_tokens: ${env.VLLM_MAX_TOKENS:4096}
+      api_token: ${env.VLLM_API_TOKEN:fake}
+      tls_verify: ${env.VLLM_TLS_VERIFY:true}
  - provider_id: sentence-transformers
    provider_type: inline::sentence-transformers
    config: {}
@ -79,7 +95,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/starter}/trace_store.db
  eval:
@ -156,72 +172,72 @@ models:
  provider_model_id: openai/chatgpt-4o-latest
  model_type: llm
 - metadata: {}
-  model_id: gpt-3.5-turbo-0125
+  model_id: openai/gpt-3.5-turbo-0125
  provider_id: openai
  provider_model_id: gpt-3.5-turbo-0125
  model_type: llm
 - metadata: {}
-  model_id: gpt-3.5-turbo
+  model_id: openai/gpt-3.5-turbo
  provider_id: openai
  provider_model_id: gpt-3.5-turbo
  model_type: llm
 - metadata: {}
-  model_id: gpt-3.5-turbo-instruct
+  model_id: openai/gpt-3.5-turbo-instruct
  provider_id: openai
  provider_model_id: gpt-3.5-turbo-instruct
  model_type: llm
 - metadata: {}
-  model_id: gpt-4
+  model_id: openai/gpt-4
  provider_id: openai
  provider_model_id: gpt-4
  model_type: llm
 - metadata: {}
-  model_id: gpt-4-turbo
+  model_id: openai/gpt-4-turbo
  provider_id: openai
  provider_model_id: gpt-4-turbo
  model_type: llm
 - metadata: {}
-  model_id: gpt-4o
+  model_id: openai/gpt-4o
  provider_id: openai
  provider_model_id: gpt-4o
  model_type: llm
 - metadata: {}
-  model_id: gpt-4o-2024-08-06
+  model_id: openai/gpt-4o-2024-08-06
  provider_id: openai
  provider_model_id: gpt-4o-2024-08-06
  model_type: llm
 - metadata: {}
-  model_id: gpt-4o-mini
+  model_id: openai/gpt-4o-mini
  provider_id: openai
  provider_model_id: gpt-4o-mini
  model_type: llm
 - metadata: {}
-  model_id: gpt-4o-audio-preview
+  model_id: openai/gpt-4o-audio-preview
  provider_id: openai
  provider_model_id: gpt-4o-audio-preview
  model_type: llm
 - metadata: {}
-  model_id: chatgpt-4o-latest
+  model_id: openai/chatgpt-4o-latest
  provider_id: openai
  provider_model_id: chatgpt-4o-latest
  model_type: llm
 - metadata: {}
-  model_id: o1
+  model_id: openai/o1
  provider_id: openai
  provider_model_id: o1
  model_type: llm
 - metadata: {}
-  model_id: o1-mini
+  model_id: openai/o1-mini
  provider_id: openai
  provider_model_id: o1-mini
  model_type: llm
 - metadata: {}
-  model_id: o3-mini
+  model_id: openai/o3-mini
  provider_id: openai
  provider_model_id: o3-mini
  model_type: llm
 - metadata: {}
-  model_id: o4-mini
+  model_id: openai/o4-mini
  provider_id: openai
  provider_model_id: o4-mini
  model_type: llm
@ -242,14 +258,14 @@ models:
 - metadata:
    embedding_dimension: 1536
    context_length: 8192
-  model_id: text-embedding-3-small
+  model_id: openai/text-embedding-3-small
  provider_id: openai
  provider_model_id: text-embedding-3-small
  model_type: embedding
 - metadata:
    embedding_dimension: 3072
    context_length: 8192
-  model_id: text-embedding-3-large
+  model_id: openai/text-embedding-3-large
  provider_id: openai
  provider_model_id: text-embedding-3-large
  model_type: embedding
@ -259,7 +275,7 @@ models:
  provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.1-8B-Instruct
+  model_id: fireworks/meta-llama/Llama-3.1-8B-Instruct
  provider_id: fireworks
  provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
  model_type: llm
@ -269,7 +285,7 @@ models:
  provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.1-70B-Instruct
+  model_id: fireworks/meta-llama/Llama-3.1-70B-Instruct
  provider_id: fireworks
  provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
  model_type: llm
@ -279,7 +295,7 @@ models:
  provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
+  model_id: fireworks/meta-llama/Llama-3.1-405B-Instruct-FP8
  provider_id: fireworks
  provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
  model_type: llm
@ -289,7 +305,7 @@ models:
  provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.2-3B-Instruct
+  model_id: fireworks/meta-llama/Llama-3.2-3B-Instruct
  provider_id: fireworks
  provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
  model_type: llm
@ -299,7 +315,7 @@ models:
  provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
+  model_id: fireworks/meta-llama/Llama-3.2-11B-Vision-Instruct
  provider_id: fireworks
  provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
  model_type: llm
@ -309,7 +325,7 @@ models:
  provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
+  model_id: fireworks/meta-llama/Llama-3.2-90B-Vision-Instruct
  provider_id: fireworks
  provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
  model_type: llm
@ -319,7 +335,7 @@ models:
  provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.3-70B-Instruct
+  model_id: fireworks/meta-llama/Llama-3.3-70B-Instruct
  provider_id: fireworks
  provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
  model_type: llm
@ -329,7 +345,7 @@ models:
  provider_model_id: accounts/fireworks/models/llama-guard-3-8b
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-Guard-3-8B
+  model_id: fireworks/meta-llama/Llama-Guard-3-8B
  provider_id: fireworks
  provider_model_id: accounts/fireworks/models/llama-guard-3-8b
  model_type: llm
@ -339,7 +355,7 @@ models:
  provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-Guard-3-11B-Vision
+  model_id: fireworks/meta-llama/Llama-Guard-3-11B-Vision
  provider_id: fireworks
  provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
  model_type: llm
@ -349,7 +365,7 @@ models:
  provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  model_id: fireworks/meta-llama/Llama-4-Scout-17B-16E-Instruct
  provider_id: fireworks
  provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
  model_type: llm
@ -359,17 +375,307 @@ models:
  provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  model_id: fireworks/meta-llama/Llama-4-Maverick-17B-128E-Instruct
  provider_id: fireworks
  provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
  model_type: llm
 - metadata:
    embedding_dimension: 768
    context_length: 8192
-  model_id: nomic-ai/nomic-embed-text-v1.5
+  model_id: fireworks/nomic-ai/nomic-embed-text-v1.5
  provider_id: fireworks
  provider_model_id: nomic-ai/nomic-embed-text-v1.5
  model_type: embedding
+- metadata: {}
+  model_id: together/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
+  provider_id: together
+  provider_model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-3.1-8B-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
+  provider_id: together
+  provider_model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-3.1-70B-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
+  provider_id: together
+  provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-3.1-405B-Instruct-FP8
+  provider_id: together
+  provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-3.2-3B-Instruct-Turbo
+  provider_id: together
+  provider_model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-3.2-3B-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
+  provider_id: together
+  provider_model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-3.2-11B-Vision-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
+  provider_id: together
+  provider_model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-3.2-90B-Vision-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-3.3-70B-Instruct-Turbo
+  provider_id: together
+  provider_model_id: meta-llama/Llama-3.3-70B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-3.3-70B-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Llama-3.3-70B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Meta-Llama-Guard-3-8B
+  provider_id: together
+  provider_model_id: meta-llama/Meta-Llama-Guard-3-8B
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-Guard-3-8B
+  provider_id: together
+  provider_model_id: meta-llama/Meta-Llama-Guard-3-8B
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-Guard-3-11B-Vision-Turbo
+  provider_id: together
+  provider_model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-Guard-3-11B-Vision
+  provider_id: together
+  provider_model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo
+  model_type: llm
+- metadata:
+    embedding_dimension: 768
+    context_length: 8192
+  model_id: togethercomputer/m2-bert-80M-8k-retrieval
+  provider_id: together
+  provider_model_id: togethercomputer/m2-bert-80M-8k-retrieval
+  model_type: embedding
+- metadata:
+    embedding_dimension: 768
+    context_length: 32768
+  model_id: togethercomputer/m2-bert-80M-32k-retrieval
+  provider_id: together
+  provider_model_id: togethercomputer/m2-bert-80M-32k-retrieval
+  model_type: embedding
+- metadata: {}
+  model_id: together/meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  provider_id: together
+  provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  provider_id: together
+  provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  model_type: llm
+- metadata: {}
+  model_id: ollama/llama3.1:8b-instruct-fp16
+  provider_id: ollama
+  provider_model_id: llama3.1:8b-instruct-fp16
+  model_type: llm
+- metadata: {}
+  model_id: ollama/meta-llama/Llama-3.1-8B-Instruct
+  provider_id: ollama
+  provider_model_id: llama3.1:8b-instruct-fp16
+  model_type: llm
+- metadata: {}
+  model_id: ollama/llama3.1:8b
+  provider_id: ollama
+  provider_model_id: llama3.1:8b
+  model_type: llm
+- metadata: {}
+  model_id: ollama/llama3.1:70b-instruct-fp16
+  provider_id: ollama
+  provider_model_id: llama3.1:70b-instruct-fp16
+  model_type: llm
+- metadata: {}
+  model_id: ollama/meta-llama/Llama-3.1-70B-Instruct
+  provider_id: ollama
+  provider_model_id: llama3.1:70b-instruct-fp16
+  model_type: llm
+- metadata: {}
+  model_id: ollama/llama3.1:70b
+  provider_id: ollama
+  provider_model_id: llama3.1:70b
+  model_type: llm
+- metadata: {}
+  model_id: ollama/llama3.1:405b-instruct-fp16
+  provider_id: ollama
+  provider_model_id: llama3.1:405b-instruct-fp16
+  model_type: llm
+- metadata: {}
+  model_id: ollama/meta-llama/Llama-3.1-405B-Instruct-FP8
+  provider_id: ollama
+  provider_model_id: llama3.1:405b-instruct-fp16
+  model_type: llm
+- metadata: {}
+  model_id: ollama/llama3.1:405b
+  provider_id: ollama
+  provider_model_id: llama3.1:405b
+  model_type: llm
+- metadata: {}
+  model_id: ollama/llama3.2:1b-instruct-fp16
+  provider_id: ollama
+  provider_model_id: llama3.2:1b-instruct-fp16
+  model_type: llm
+- metadata: {}
+  model_id: ollama/meta-llama/Llama-3.2-1B-Instruct
+  provider_id: ollama
+  provider_model_id: llama3.2:1b-instruct-fp16
+  model_type: llm
+- metadata: {}
+  model_id: ollama/llama3.2:1b
+  provider_id: ollama
+  provider_model_id: llama3.2:1b
+  model_type: llm
+- metadata: {}
+  model_id: ollama/llama3.2:3b-instruct-fp16
+  provider_id: ollama
+  provider_model_id: llama3.2:3b-instruct-fp16
+  model_type: llm
+- metadata: {}
+  model_id: ollama/meta-llama/Llama-3.2-3B-Instruct
+  provider_id: ollama
+  provider_model_id: llama3.2:3b-instruct-fp16
+  model_type: llm
+- metadata: {}
+  model_id: ollama/llama3.2:3b
+  provider_id: ollama
+  provider_model_id: llama3.2:3b
+  model_type: llm
+- metadata: {}
+  model_id: ollama/llama3.2-vision:11b-instruct-fp16
+  provider_id: ollama
+  provider_model_id: llama3.2-vision:11b-instruct-fp16
+  model_type: llm
+- metadata: {}
+  model_id: ollama/meta-llama/Llama-3.2-11B-Vision-Instruct
+  provider_id: ollama
+  provider_model_id: llama3.2-vision:11b-instruct-fp16
+  model_type: llm
+- metadata: {}
+  model_id: ollama/llama3.2-vision:latest
+  provider_id: ollama
+  provider_model_id: llama3.2-vision:latest
+  model_type: llm
+- metadata: {}
+  model_id: ollama/llama3.2-vision:90b-instruct-fp16
+  provider_id: ollama
+  provider_model_id: llama3.2-vision:90b-instruct-fp16
+  model_type: llm
+- metadata: {}
+  model_id: ollama/meta-llama/Llama-3.2-90B-Vision-Instruct
+  provider_id: ollama
+  provider_model_id: llama3.2-vision:90b-instruct-fp16
+  model_type: llm
+- metadata: {}
+  model_id: ollama/llama3.2-vision:90b
+  provider_id: ollama
+  provider_model_id: llama3.2-vision:90b
+  model_type: llm
+- metadata: {}
+  model_id: ollama/llama3.3:70b
+  provider_id: ollama
+  provider_model_id: llama3.3:70b
+  model_type: llm
+- metadata: {}
+  model_id: ollama/meta-llama/Llama-3.3-70B-Instruct
+  provider_id: ollama
+  provider_model_id: llama3.3:70b
+  model_type: llm
+- metadata: {}
+  model_id: ollama/llama-guard3:8b
+  provider_id: ollama
+  provider_model_id: llama-guard3:8b
+  model_type: llm
+- metadata: {}
+  model_id: ollama/meta-llama/Llama-Guard-3-8B
+  provider_id: ollama
+  provider_model_id: llama-guard3:8b
+  model_type: llm
+- metadata: {}
+  model_id: ollama/llama-guard3:1b
+  provider_id: ollama
+  provider_model_id: llama-guard3:1b
+  model_type: llm
+- metadata: {}
+  model_id: ollama/meta-llama/Llama-Guard-3-1B
+  provider_id: ollama
+  provider_model_id: llama-guard3:1b
+  model_type: llm
+- metadata:
+    embedding_dimension: 384
+    context_length: 512
+  model_id: ollama/all-minilm:latest
+  provider_id: ollama
+  provider_model_id: all-minilm:latest
+  model_type: embedding
+- metadata:
+    embedding_dimension: 384
+    context_length: 512
+  model_id: ollama/all-minilm
+  provider_id: ollama
+  provider_model_id: all-minilm:latest
+  model_type: embedding
+- metadata:
+    embedding_dimension: 768
+    context_length: 8192
+  model_id: ollama/nomic-embed-text
+  provider_id: ollama
+  provider_model_id: nomic-embed-text
+  model_type: embedding
 - metadata: {}
  model_id: anthropic/claude-3-5-sonnet-latest
  provider_id: anthropic
@ -429,7 +735,7 @@ models:
  provider_model_id: groq/llama3-8b-8192
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.1-8B-Instruct
+  model_id: groq/meta-llama/Llama-3.1-8B-Instruct
  provider_id: groq
  provider_model_id: groq/llama3-8b-8192
  model_type: llm
@ -444,7 +750,7 @@ models:
  provider_model_id: groq/llama3-70b-8192
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3-70B-Instruct
+  model_id: groq/meta-llama/Llama-3-70B-Instruct
  provider_id: groq
  provider_model_id: groq/llama3-70b-8192
  model_type: llm
@ -454,7 +760,7 @@ models:
  provider_model_id: groq/llama-3.3-70b-versatile
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.3-70B-Instruct
+  model_id: groq/meta-llama/Llama-3.3-70B-Instruct
  provider_id: groq
  provider_model_id: groq/llama-3.3-70b-versatile
  model_type: llm
@ -464,7 +770,7 @@ models:
  provider_model_id: groq/llama-3.2-3b-preview
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.2-3B-Instruct
+  model_id: groq/meta-llama/Llama-3.2-3B-Instruct
  provider_id: groq
  provider_model_id: groq/llama-3.2-3b-preview
  model_type: llm
@ -474,7 +780,7 @@ models:
  provider_model_id: groq/llama-4-scout-17b-16e-instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  model_id: groq/meta-llama/Llama-4-Scout-17B-16E-Instruct
  provider_id: groq
  provider_model_id: groq/llama-4-scout-17b-16e-instruct
  model_type: llm
@ -484,7 +790,7 @@ models:
  provider_model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  model_id: groq/meta-llama/Llama-4-Scout-17B-16E-Instruct
  provider_id: groq
  provider_model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
  model_type: llm
@ -494,7 +800,7 @@ models:
  provider_model_id: groq/llama-4-maverick-17b-128e-instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  model_id: groq/meta-llama/Llama-4-Maverick-17B-128E-Instruct
  provider_id: groq
  provider_model_id: groq/llama-4-maverick-17b-128e-instruct
  model_type: llm
@ -504,7 +810,7 @@ models:
  provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  model_id: groq/meta-llama/Llama-4-Maverick-17B-128E-Instruct
  provider_id: groq
  provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
  model_type: llm
@ -514,7 +820,7 @@ models:
  provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.1-8B-Instruct
+  model_id: sambanova/meta-llama/Llama-3.1-8B-Instruct
  provider_id: sambanova
  provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct
  model_type: llm
@ -524,7 +830,7 @@ models:
  provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
+  model_id: sambanova/meta-llama/Llama-3.1-405B-Instruct-FP8
  provider_id: sambanova
  provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct
  model_type: llm
@ -534,7 +840,7 @@ models:
  provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.2-1B-Instruct
+  model_id: sambanova/meta-llama/Llama-3.2-1B-Instruct
  provider_id: sambanova
  provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct
  model_type: llm
@ -544,7 +850,7 @@ models:
  provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.2-3B-Instruct
+  model_id: sambanova/meta-llama/Llama-3.2-3B-Instruct
  provider_id: sambanova
  provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct
  model_type: llm
@ -554,7 +860,7 @@ models:
  provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.3-70B-Instruct
+  model_id: sambanova/meta-llama/Llama-3.3-70B-Instruct
  provider_id: sambanova
  provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct
  model_type: llm
@ -564,7 +870,7 @@ models:
  provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
+  model_id: sambanova/meta-llama/Llama-3.2-11B-Vision-Instruct
  provider_id: sambanova
  provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct
  model_type: llm
@ -574,7 +880,7 @@ models:
  provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
+  model_id: sambanova/meta-llama/Llama-3.2-90B-Vision-Instruct
  provider_id: sambanova
  provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct
  model_type: llm
@ -584,7 +890,7 @@ models:
  provider_model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  model_id: sambanova/meta-llama/Llama-4-Scout-17B-16E-Instruct
  provider_id: sambanova
  provider_model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
  model_type: llm
@ -594,7 +900,7 @@ models:
  provider_model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  model_id: sambanova/meta-llama/Llama-4-Maverick-17B-128E-Instruct
  provider_id: sambanova
  provider_model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
  model_type: llm
@ -604,7 +910,7 @@ models:
  provider_model_id: sambanova/Meta-Llama-Guard-3-8B
  model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-Guard-3-8B
+  model_id: sambanova/meta-llama/Llama-Guard-3-8B
  provider_id: sambanova
  provider_model_id: sambanova/Meta-Llama-Guard-3-8B
  model_type: llm
--- a/llama_stack/templates/starter/starter.py
+++ b/llama_stack/templates/starter/starter.py
@ -34,6 +34,10 @@ from llama_stack.providers.remote.inference.groq.config import GroqConfig
 from llama_stack.providers.remote.inference.groq.models import (
    MODEL_ENTRIES as GROQ_MODEL_ENTRIES,
 )
+from llama_stack.providers.remote.inference.ollama.config import OllamaImplConfig
+from llama_stack.providers.remote.inference.ollama.models import (
+    MODEL_ENTRIES as OLLAMA_MODEL_ENTRIES,
+)
 from llama_stack.providers.remote.inference.openai.config import OpenAIConfig
 from llama_stack.providers.remote.inference.openai.models import (
    MODEL_ENTRIES as OPENAI_MODEL_ENTRIES,
@ -42,11 +46,17 @@ from llama_stack.providers.remote.inference.sambanova.config import SambaNovaImp
 from llama_stack.providers.remote.inference.sambanova.models import (
    MODEL_ENTRIES as SAMBANOVA_MODEL_ENTRIES,
 )
+from llama_stack.providers.remote.inference.together.config import TogetherImplConfig
+from llama_stack.providers.remote.inference.together.models import (
+    MODEL_ENTRIES as TOGETHER_MODEL_ENTRIES,
+)
+from llama_stack.providers.remote.inference.vllm import VLLMInferenceAdapterConfig
 from llama_stack.providers.remote.vector_io.chroma.config import ChromaVectorIOConfig
 from llama_stack.providers.remote.vector_io.pgvector.config import (
    PGVectorVectorIOConfig,
 )
 from llama_stack.providers.utils.inference.model_registry import ProviderModelEntry
+from llama_stack.providers.utils.sqlstore.sqlstore import PostgresSqlStoreConfig
 from llama_stack.templates.template import (
    DistributionTemplate,
    RunConfigSettings,
@ -67,6 +77,16 @@ def get_inference_providers() -> tuple[list[Provider], dict[str, list[ProviderMo
            FIREWORKS_MODEL_ENTRIES,
            FireworksImplConfig.sample_run_config(api_key="${env.FIREWORKS_API_KEY:}"),
        ),
+        (
+            "together",
+            TOGETHER_MODEL_ENTRIES,
+            TogetherImplConfig.sample_run_config(api_key="${env.TOGETHER_API_KEY:}"),
+        ),
+        (
+            "ollama",
+            OLLAMA_MODEL_ENTRIES,
+            OllamaImplConfig.sample_run_config(),
+        ),
        (
            "anthropic",
            ANTHROPIC_MODEL_ENTRIES,
@ -87,6 +107,13 @@ def get_inference_providers() -> tuple[list[Provider], dict[str, list[ProviderMo
            SAMBANOVA_MODEL_ENTRIES,
            SambaNovaImplConfig.sample_run_config(api_key="${env.SAMBANOVA_API_KEY:}"),
        ),
+        (
+            "vllm",
+            [],
+            VLLMInferenceAdapterConfig.sample_run_config(
+                url="${env.VLLM_URL:http://localhost:8000/v1}",
+            ),
+        ),
    ]
    inference_providers = []
    available_models = {}
@ -169,6 +196,8 @@ def get_distribution_template() -> DistributionTemplate:
    )

    default_models = get_model_registry(available_models)
+
+    postgres_store = PostgresSqlStoreConfig.sample_run_config()
    return DistributionTemplate(
        name=name,
        distro_type="self_hosted",
@ -177,6 +206,7 @@ def get_distribution_template() -> DistributionTemplate:
        template_path=None,
        providers=providers,
        available_models_by_provider=available_models,
+        additional_pip_packages=postgres_store.pip_packages,
        run_configs={
            "run.yaml": RunConfigSettings(
                provider_overrides={
@ -201,5 +231,25 @@ def get_distribution_template() -> DistributionTemplate:
                "",
                "OpenAI API Key",
            ),
+            "GROQ_API_KEY": (
+                "",
+                "Groq API Key",
+            ),
+            "ANTHROPIC_API_KEY": (
+                "",
+                "Anthropic API Key",
+            ),
+            "GEMINI_API_KEY": (
+                "",
+                "Gemini API Key",
+            ),
+            "SAMBANOVA_API_KEY": (
+                "",
+                "SambaNova API Key",
+            ),
+            "VLLM_URL": (
+                "http://localhost:8000/v1",
+                "VLLM URL",
+            ),
        },
    )
--- a/llama_stack/templates/template.py
+++ b/llama_stack/templates/template.py
@ -8,6 +8,7 @@ from pathlib import Path
 from typing import Literal

 import jinja2
+import rich
 import yaml
 from pydantic import BaseModel, Field

@ -28,21 +29,43 @@ from llama_stack.distribution.datatypes import (
 from llama_stack.distribution.distribution import get_provider_registry
 from llama_stack.distribution.utils.dynamic import instantiate_class_type
 from llama_stack.providers.utils.inference.model_registry import ProviderModelEntry
-from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
-from llama_stack.providers.utils.sqlstore.sqlstore import SqliteSqlStoreConfig
+from llama_stack.providers.utils.kvstore.config import KVStoreConfig, SqliteKVStoreConfig
+from llama_stack.providers.utils.sqlstore.sqlstore import SqliteSqlStoreConfig, SqlStoreConfig


 def get_model_registry(
    available_models: dict[str, list[ProviderModelEntry]],
 ) -> list[ModelInput]:
    models = []
+
+    # check for conflicts in model ids
+    all_ids = set()
+    ids_conflict = False
+
+    for _, entries in available_models.items():
+        for entry in entries:
+            ids = [entry.provider_model_id] + entry.aliases
+            for model_id in ids:
+                if model_id in all_ids:
+                    ids_conflict = True
+                    rich.print(
+                        f"[yellow]Model id {model_id} conflicts; all model ids will be prefixed with provider id[/yellow]"
+                    )
+                    break
+            all_ids.update(ids)
+            if ids_conflict:
+                break
+        if ids_conflict:
+            break
+
    for provider_id, entries in available_models.items():
        for entry in entries:
            ids = [entry.provider_model_id] + entry.aliases
            for model_id in ids:
+                identifier = f"{provider_id}/{model_id}" if ids_conflict and provider_id not in model_id else model_id
                models.append(
                    ModelInput(
-                        model_id=model_id,
+                        model_id=identifier,
                        provider_model_id=entry.provider_model_id,
                        provider_id=provider_id,
                        model_type=entry.model_type,
@ -64,6 +87,8 @@ class RunConfigSettings(BaseModel):
    default_tool_groups: list[ToolGroupInput] | None = None
    default_datasets: list[DatasetInput] | None = None
    default_benchmarks: list[BenchmarkInput] | None = None
+    metadata_store: KVStoreConfig | None = None
+    inference_store: SqlStoreConfig | None = None

    def run_config(
        self,
@ -114,11 +139,13 @@ class RunConfigSettings(BaseModel):
            container_image=container_image,
            apis=apis,
            providers=provider_configs,
-            metadata_store=SqliteKVStoreConfig.sample_run_config(
+            metadata_store=self.metadata_store
+            or SqliteKVStoreConfig.sample_run_config(
                __distro_dir__=f"~/.llama/distributions/{name}",
                db_name="registry.db",
            ),
-            inference_store=SqliteSqlStoreConfig.sample_run_config(
+            inference_store=self.inference_store
+            or SqliteSqlStoreConfig.sample_run_config(
                __distro_dir__=f"~/.llama/distributions/{name}",
                db_name="inference_store.db",
            ),
@ -150,12 +177,26 @@ class DistributionTemplate(BaseModel):

    available_models_by_provider: dict[str, list[ProviderModelEntry]] | None = None

+    # we may want to specify additional pip packages without necessarily indicating a
+    # specific "default" inference store (which is what typically used to dictate additional
+    # pip packages)
+    additional_pip_packages: list[str] | None = None
+
    def build_config(self) -> BuildConfig:
        additional_pip_packages: list[str] = []
        for run_config in self.run_configs.values():
            run_config_ = run_config.run_config(self.name, self.providers, self.container_image)
+
+            # TODO: This is a hack to get the dependencies for internal APIs into build
+            # We should have a better way to do this by formalizing the concept of "internal" APIs
+            # and providers, with a way to specify dependencies for them.
            if run_config_.inference_store:
                additional_pip_packages.extend(run_config_.inference_store.pip_packages)
+            if run_config_.metadata_store:
+                additional_pip_packages.extend(run_config_.metadata_store.pip_packages)
+
+        if self.additional_pip_packages:
+            additional_pip_packages.extend(self.additional_pip_packages)

        return BuildConfig(
            distribution_spec=DistributionSpec(
@ -164,7 +205,7 @@ class DistributionTemplate(BaseModel):
                providers=self.providers,
            ),
            image_type="conda",  # default to conda, can be overridden
-            additional_pip_packages=additional_pip_packages,
+            additional_pip_packages=sorted(set(additional_pip_packages)),
        )

    def generate_markdown_docs(self) -> str:
--- a/llama_stack/templates/tgi/build.yaml
+++ b/llama_stack/templates/tgi/build.yaml
@ -31,5 +31,5 @@ distribution_spec:
    - remote::model-context-protocol
 image_type: conda
 additional_pip_packages:
- sqlalchemy[asyncio]
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/tgi/run-with-safety.yaml
+++ b/llama_stack/templates/tgi/run-with-safety.yaml
@ -48,7 +48,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/trace_store.db
  eval:
--- a/llama_stack/templates/tgi/run.yaml
+++ b/llama_stack/templates/tgi/run.yaml
@ -47,7 +47,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/trace_store.db
  eval:
--- a/llama_stack/templates/together/build.yaml
+++ b/llama_stack/templates/together/build.yaml
@ -32,5 +32,5 @@ distribution_spec:
    - remote::wolfram-alpha
 image_type: conda
 additional_pip_packages:
- sqlalchemy[asyncio]
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/together/run-with-safety.yaml
+++ b/llama_stack/templates/together/run-with-safety.yaml
@ -53,7 +53,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/trace_store.db
  eval:
--- a/llama_stack/templates/together/run.yaml
+++ b/llama_stack/templates/together/run.yaml
@ -48,7 +48,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/trace_store.db
  eval:
--- a/llama_stack/templates/verification/build.yaml
+++ b/llama_stack/templates/verification/build.yaml
@ -1,39 +0,0 @@
-version: '2'
-distribution_spec:
-  description: Distribution for running e2e tests in CI
-  providers:
-    inference:
-    - remote::openai
-    - remote::fireworks-openai-compat
-    - remote::together-openai-compat
-    - remote::groq-openai-compat
-    - remote::sambanova-openai-compat
-    - remote::cerebras-openai-compat
-    - inline::sentence-transformers
-    vector_io:
-    - inline::sqlite-vec
-    - remote::chromadb
-    - remote::pgvector
-    safety:
-    - inline::llama-guard
-    agents:
-    - inline::meta-reference
-    telemetry:
-    - inline::meta-reference
-    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::rag-runtime
-    - remote::model-context-protocol
-image_type: conda
-additional_pip_packages:
- sqlalchemy[asyncio]
--- a/llama_stack/templates/verification/run.yaml
+++ b/llama_stack/templates/verification/run.yaml
@ -1,731 +0,0 @@
-version: '2'
-image_name: verification
-apis:
- agents
- datasetio
- eval
- inference
- safety
- scoring
- telemetry
- tool_runtime
- vector_io
-providers:
-  inference:
-  - provider_id: openai
-    provider_type: remote::openai
-    config:
-      api_key: ${env.OPENAI_API_KEY:}
-  - provider_id: fireworks-openai-compat
-    provider_type: remote::fireworks-openai-compat
-    config:
-      openai_compat_api_base: https://api.fireworks.ai/inference/v1
-      api_key: ${env.FIREWORKS_API_KEY:}
-  - provider_id: together-openai-compat
-    provider_type: remote::together-openai-compat
-    config:
-      openai_compat_api_base: https://api.together.xyz/v1
-      api_key: ${env.TOGETHER_API_KEY:}
-  - provider_id: groq-openai-compat
-    provider_type: remote::groq-openai-compat
-    config:
-      openai_compat_api_base: https://api.groq.com/openai/v1
-      api_key: ${env.GROQ_API_KEY:}
-  - provider_id: sambanova-openai-compat
-    provider_type: remote::sambanova-openai-compat
-    config:
-      openai_compat_api_base: https://api.sambanova.ai/v1
-      api_key: ${env.SAMBANOVA_API_KEY:}
-  - provider_id: cerebras-openai-compat
-    provider_type: remote::cerebras-openai-compat
-    config:
-      openai_compat_api_base: https://api.cerebras.ai/v1
-      api_key: ${env.CEREBRAS_API_KEY:}
-  - provider_id: sentence-transformers
-    provider_type: inline::sentence-transformers
-    config: {}
-  vector_io:
-  - provider_id: sqlite-vec
-    provider_type: inline::sqlite-vec
-    config:
-      db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/sqlite_vec.db
-  - provider_id: ${env.ENABLE_CHROMADB+chromadb}
-    provider_type: remote::chromadb
-    config:
-      url: ${env.CHROMADB_URL:}
-  - provider_id: ${env.ENABLE_PGVECTOR+pgvector}
-    provider_type: remote::pgvector
-    config:
-      host: ${env.PGVECTOR_HOST:localhost}
-      port: ${env.PGVECTOR_PORT:5432}
-      db: ${env.PGVECTOR_DB:}
-      user: ${env.PGVECTOR_USER:}
-      password: ${env.PGVECTOR_PASSWORD:}
-  safety:
-  - provider_id: llama-guard
-    provider_type: inline::llama-guard
-    config:
-      excluded_categories: []
-  agents:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      persistence_store:
-        type: sqlite
-        namespace: null
-        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/agents_store.db
-      responses_store:
-        type: sqlite
-        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/responses_store.db
-  telemetry:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
-      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
-      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/trace_store.db
-  eval:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      kvstore:
-        type: sqlite
-        namespace: null
-        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/meta_reference_eval.db
-  datasetio:
-  - provider_id: huggingface
-    provider_type: remote::huggingface
-    config:
-      kvstore:
-        type: sqlite
-        namespace: null
-        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/huggingface_datasetio.db
-  - provider_id: localfs
-    provider_type: inline::localfs
-    config:
-      kvstore:
-        type: sqlite
-        namespace: null
-        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/localfs_datasetio.db
-  scoring:
-  - provider_id: basic
-    provider_type: inline::basic
-    config: {}
-  - provider_id: llm-as-judge
-    provider_type: inline::llm-as-judge
-    config: {}
-  - provider_id: braintrust
-    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: rag-runtime
-    provider_type: inline::rag-runtime
-    config: {}
-  - provider_id: model-context-protocol
-    provider_type: remote::model-context-protocol
-    config: {}
-metadata_store:
-  type: sqlite
-  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/registry.db
-inference_store:
-  type: sqlite
-  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/inference_store.db
-models:
- metadata: {}
-  model_id: openai/gpt-4o
-  provider_id: openai
-  provider_model_id: openai/gpt-4o
-  model_type: llm
- metadata: {}
-  model_id: openai/gpt-4o-mini
-  provider_id: openai
-  provider_model_id: openai/gpt-4o-mini
-  model_type: llm
- metadata: {}
-  model_id: openai/chatgpt-4o-latest
-  provider_id: openai
-  provider_model_id: openai/chatgpt-4o-latest
-  model_type: llm
- metadata: {}
-  model_id: gpt-3.5-turbo-0125
-  provider_id: openai
-  provider_model_id: gpt-3.5-turbo-0125
-  model_type: llm
- metadata: {}
-  model_id: gpt-3.5-turbo
-  provider_id: openai
-  provider_model_id: gpt-3.5-turbo
-  model_type: llm
- metadata: {}
-  model_id: gpt-3.5-turbo-instruct
-  provider_id: openai
-  provider_model_id: gpt-3.5-turbo-instruct
-  model_type: llm
- metadata: {}
-  model_id: gpt-4
-  provider_id: openai
-  provider_model_id: gpt-4
-  model_type: llm
- metadata: {}
-  model_id: gpt-4-turbo
-  provider_id: openai
-  provider_model_id: gpt-4-turbo
-  model_type: llm
- metadata: {}
-  model_id: gpt-4o
-  provider_id: openai
-  provider_model_id: gpt-4o
-  model_type: llm
- metadata: {}
-  model_id: gpt-4o-2024-08-06
-  provider_id: openai
-  provider_model_id: gpt-4o-2024-08-06
-  model_type: llm
- metadata: {}
-  model_id: gpt-4o-mini
-  provider_id: openai
-  provider_model_id: gpt-4o-mini
-  model_type: llm
- metadata: {}
-  model_id: gpt-4o-audio-preview
-  provider_id: openai
-  provider_model_id: gpt-4o-audio-preview
-  model_type: llm
- metadata: {}
-  model_id: chatgpt-4o-latest
-  provider_id: openai
-  provider_model_id: chatgpt-4o-latest
-  model_type: llm
- metadata: {}
-  model_id: o1
-  provider_id: openai
-  provider_model_id: o1
-  model_type: llm
- metadata: {}
-  model_id: o1-mini
-  provider_id: openai
-  provider_model_id: o1-mini
-  model_type: llm
- metadata: {}
-  model_id: o3-mini
-  provider_id: openai
-  provider_model_id: o3-mini
-  model_type: llm
- metadata: {}
-  model_id: o4-mini
-  provider_id: openai
-  provider_model_id: o4-mini
-  model_type: llm
- metadata:
-    embedding_dimension: 1536
-    context_length: 8192
-  model_id: openai/text-embedding-3-small
-  provider_id: openai
-  provider_model_id: openai/text-embedding-3-small
-  model_type: embedding
- metadata:
-    embedding_dimension: 3072
-    context_length: 8192
-  model_id: openai/text-embedding-3-large
-  provider_id: openai
-  provider_model_id: openai/text-embedding-3-large
-  model_type: embedding
- metadata:
-    embedding_dimension: 1536
-    context_length: 8192
-  model_id: text-embedding-3-small
-  provider_id: openai
-  provider_model_id: text-embedding-3-small
-  model_type: embedding
- metadata:
-    embedding_dimension: 3072
-    context_length: 8192
-  model_id: text-embedding-3-large
-  provider_id: openai
-  provider_model_id: text-embedding-3-large
-  model_type: embedding
- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.1-8B-Instruct
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
-  model_type: llm
- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.1-70B-Instruct
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
-  model_type: llm
- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
-  model_type: llm
- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-3B-Instruct
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
-  model_type: llm
- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
-  model_type: llm
- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
-  model_type: llm
- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.3-70B-Instruct
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
-  model_type: llm
- metadata: {}
-  model_id: accounts/fireworks/models/llama-guard-3-8b
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama-guard-3-8b
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-Guard-3-8B
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama-guard-3-8b
-  model_type: llm
- metadata: {}
-  model_id: accounts/fireworks/models/llama-guard-3-11b-vision
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-Guard-3-11B-Vision
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
-  model_type: llm
- metadata: {}
-  model_id: accounts/fireworks/models/llama4-scout-instruct-basic
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
-  model_type: llm
- metadata: {}
-  model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
-  provider_id: fireworks-openai-compat
-  provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
-  model_type: llm
- metadata:
-    embedding_dimension: 768
-    context_length: 8192
-  model_id: nomic-ai/nomic-embed-text-v1.5
-  provider_id: fireworks-openai-compat
-  provider_model_id: nomic-ai/nomic-embed-text-v1.5
-  model_type: embedding
- metadata: {}
-  model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.1-8B-Instruct
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.1-70B-Instruct
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-3B-Instruct
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.3-70B-Instruct-Turbo
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Llama-3.3-70B-Instruct-Turbo
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.3-70B-Instruct
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Llama-3.3-70B-Instruct-Turbo
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Meta-Llama-Guard-3-8B
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Meta-Llama-Guard-3-8B
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-Guard-3-8B
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Meta-Llama-Guard-3-8B
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-Guard-3-11B-Vision
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo
-  model_type: llm
- metadata:
-    embedding_dimension: 768
-    context_length: 8192
-  model_id: togethercomputer/m2-bert-80M-8k-retrieval
-  provider_id: together-openai-compat
-  provider_model_id: togethercomputer/m2-bert-80M-8k-retrieval
-  model_type: embedding
- metadata:
-    embedding_dimension: 768
-    context_length: 32768
-  model_id: togethercomputer/m2-bert-80M-32k-retrieval
-  provider_id: together-openai-compat
-  provider_model_id: togethercomputer/m2-bert-80M-32k-retrieval
-  model_type: embedding
- metadata: {}
-  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
-  model_type: llm
- metadata: {}
-  model_id: together/meta-llama/Llama-4-Scout-17B-16E-Instruct
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
-  model_type: llm
- metadata: {}
-  model_id: together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
-  provider_id: together-openai-compat
-  provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
-  model_type: llm
- metadata: {}
-  model_id: groq/llama3-8b-8192
-  provider_id: groq-openai-compat
-  provider_model_id: groq/llama3-8b-8192
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.1-8B-Instruct
-  provider_id: groq-openai-compat
-  provider_model_id: groq/llama3-8b-8192
-  model_type: llm
- metadata: {}
-  model_id: groq/llama-3.1-8b-instant
-  provider_id: groq-openai-compat
-  provider_model_id: groq/llama-3.1-8b-instant
-  model_type: llm
- metadata: {}
-  model_id: groq/llama3-70b-8192
-  provider_id: groq-openai-compat
-  provider_model_id: groq/llama3-70b-8192
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3-70B-Instruct
-  provider_id: groq-openai-compat
-  provider_model_id: groq/llama3-70b-8192
-  model_type: llm
- metadata: {}
-  model_id: groq/llama-3.3-70b-versatile
-  provider_id: groq-openai-compat
-  provider_model_id: groq/llama-3.3-70b-versatile
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.3-70B-Instruct
-  provider_id: groq-openai-compat
-  provider_model_id: groq/llama-3.3-70b-versatile
-  model_type: llm
- metadata: {}
-  model_id: groq/llama-3.2-3b-preview
-  provider_id: groq-openai-compat
-  provider_model_id: groq/llama-3.2-3b-preview
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-3B-Instruct
-  provider_id: groq-openai-compat
-  provider_model_id: groq/llama-3.2-3b-preview
-  model_type: llm
- metadata: {}
-  model_id: groq/llama-4-scout-17b-16e-instruct
-  provider_id: groq-openai-compat
-  provider_model_id: groq/llama-4-scout-17b-16e-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
-  provider_id: groq-openai-compat
-  provider_model_id: groq/llama-4-scout-17b-16e-instruct
-  model_type: llm
- metadata: {}
-  model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
-  provider_id: groq-openai-compat
-  provider_model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
-  provider_id: groq-openai-compat
-  provider_model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
-  model_type: llm
- metadata: {}
-  model_id: groq/llama-4-maverick-17b-128e-instruct
-  provider_id: groq-openai-compat
-  provider_model_id: groq/llama-4-maverick-17b-128e-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
-  provider_id: groq-openai-compat
-  provider_model_id: groq/llama-4-maverick-17b-128e-instruct
-  model_type: llm
- metadata: {}
-  model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
-  provider_id: groq-openai-compat
-  provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
-  provider_id: groq-openai-compat
-  provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
-  model_type: llm
- metadata: {}
-  model_id: sambanova/Meta-Llama-3.1-8B-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.1-8B-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: sambanova/Meta-Llama-3.1-405B-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: sambanova/Meta-Llama-3.2-1B-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-1B-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: sambanova/Meta-Llama-3.2-3B-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-3B-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: sambanova/Meta-Llama-3.3-70B-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.3-70B-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: sambanova/Llama-3.2-11B-Vision-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct
-  model_type: llm
- metadata: {}
-  model_id: sambanova/Llama-3.2-90B-Vision-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct
-  model_type: llm
- metadata: {}
-  model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
-  model_type: llm
- metadata: {}
-  model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
-  model_type: llm
- metadata: {}
-  model_id: sambanova/Meta-Llama-Guard-3-8B
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Meta-Llama-Guard-3-8B
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-Guard-3-8B
-  provider_id: sambanova-openai-compat
-  provider_model_id: sambanova/Meta-Llama-Guard-3-8B
-  model_type: llm
- metadata: {}
-  model_id: llama3.1-8b
-  provider_id: cerebras-openai-compat
-  provider_model_id: llama3.1-8b
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.1-8B-Instruct
-  provider_id: cerebras-openai-compat
-  provider_model_id: llama3.1-8b
-  model_type: llm
- metadata: {}
-  model_id: llama-3.3-70b
-  provider_id: cerebras-openai-compat
-  provider_model_id: llama-3.3-70b
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.3-70B-Instruct
-  provider_id: cerebras-openai-compat
-  provider_model_id: llama-3.3-70b
-  model_type: llm
- metadata:
-    embedding_dimension: 384
-  model_id: all-MiniLM-L6-v2
-  provider_id: sentence-transformers
-  model_type: embedding
-shields:
- shield_id: meta-llama/Llama-Guard-3-8B
-vector_dbs: []
-datasets: []
-scoring_fns: []
-benchmarks: []
-tool_groups:
- toolgroup_id: builtin::websearch
-  provider_id: tavily-search
- toolgroup_id: builtin::rag
-  provider_id: rag-runtime
-server:
-  port: 8321
--- a/llama_stack/templates/verification/verification.py
+++ b/llama_stack/templates/verification/verification.py
@ -1,201 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-
-from llama_stack.apis.models.models import ModelType
-from llama_stack.distribution.datatypes import (
-    ModelInput,
-    Provider,
-    ShieldInput,
-    ToolGroupInput,
-)
-from llama_stack.providers.inline.inference.sentence_transformers import (
-    SentenceTransformersInferenceConfig,
-)
-from llama_stack.providers.inline.vector_io.sqlite_vec.config import (
-    SQLiteVectorIOConfig,
-)
-from llama_stack.providers.remote.inference.cerebras.models import MODEL_ENTRIES as CEREBRAS_MODEL_ENTRIES
-from llama_stack.providers.remote.inference.cerebras_openai_compat.config import CerebrasCompatConfig
-from llama_stack.providers.remote.inference.fireworks.models import (
-    MODEL_ENTRIES as FIREWORKS_MODEL_ENTRIES,
-)
-from llama_stack.providers.remote.inference.fireworks_openai_compat.config import FireworksCompatConfig
-from llama_stack.providers.remote.inference.groq.models import (
-    MODEL_ENTRIES as GROQ_MODEL_ENTRIES,
-)
-from llama_stack.providers.remote.inference.groq_openai_compat.config import GroqCompatConfig
-from llama_stack.providers.remote.inference.openai.config import OpenAIConfig
-from llama_stack.providers.remote.inference.openai.models import (
-    MODEL_ENTRIES as OPENAI_MODEL_ENTRIES,
-)
-from llama_stack.providers.remote.inference.sambanova.models import MODEL_ENTRIES as SAMBANOVA_MODEL_ENTRIES
-from llama_stack.providers.remote.inference.sambanova_openai_compat.config import SambaNovaCompatConfig
-from llama_stack.providers.remote.inference.together.models import (
-    MODEL_ENTRIES as TOGETHER_MODEL_ENTRIES,
-)
-from llama_stack.providers.remote.inference.together_openai_compat.config import TogetherCompatConfig
-from llama_stack.providers.remote.vector_io.chroma.config import ChromaVectorIOConfig
-from llama_stack.providers.remote.vector_io.pgvector.config import (
-    PGVectorVectorIOConfig,
-)
-from llama_stack.providers.utils.inference.model_registry import ProviderModelEntry
-from llama_stack.templates.template import (
-    DistributionTemplate,
-    RunConfigSettings,
-    get_model_registry,
-)
-
-
-def get_inference_providers() -> tuple[list[Provider], dict[str, list[ProviderModelEntry]]]:
-    # in this template, we allow each API key to be optional
-    providers = [
-        (
-            "openai",
-            OPENAI_MODEL_ENTRIES,
-            OpenAIConfig.sample_run_config(api_key="${env.OPENAI_API_KEY:}"),
-        ),
-        (
-            "fireworks-openai-compat",
-            FIREWORKS_MODEL_ENTRIES,
-            FireworksCompatConfig.sample_run_config(api_key="${env.FIREWORKS_API_KEY:}"),
-        ),
-        (
-            "together-openai-compat",
-            TOGETHER_MODEL_ENTRIES,
-            TogetherCompatConfig.sample_run_config(api_key="${env.TOGETHER_API_KEY:}"),
-        ),
-        (
-            "groq-openai-compat",
-            GROQ_MODEL_ENTRIES,
-            GroqCompatConfig.sample_run_config(api_key="${env.GROQ_API_KEY:}"),
-        ),
-        (
-            "sambanova-openai-compat",
-            SAMBANOVA_MODEL_ENTRIES,
-            SambaNovaCompatConfig.sample_run_config(api_key="${env.SAMBANOVA_API_KEY:}"),
-        ),
-        (
-            "cerebras-openai-compat",
-            CEREBRAS_MODEL_ENTRIES,
-            CerebrasCompatConfig.sample_run_config(api_key="${env.CEREBRAS_API_KEY:}"),
-        ),
-    ]
-    inference_providers = []
-    available_models = {}
-    for provider_id, model_entries, config in providers:
-        inference_providers.append(
-            Provider(
-                provider_id=provider_id,
-                provider_type=f"remote::{provider_id}",
-                config=config,
-            )
-        )
-        available_models[provider_id] = model_entries
-    return inference_providers, available_models
-
-
-def get_distribution_template() -> DistributionTemplate:
-    inference_providers, available_models = get_inference_providers()
-    providers = {
-        "inference": ([p.provider_type for p in inference_providers] + ["inline::sentence-transformers"]),
-        "vector_io": ["inline::sqlite-vec", "remote::chromadb", "remote::pgvector"],
-        "safety": ["inline::llama-guard"],
-        "agents": ["inline::meta-reference"],
-        "telemetry": ["inline::meta-reference"],
-        "eval": ["inline::meta-reference"],
-        "datasetio": ["remote::huggingface", "inline::localfs"],
-        "scoring": ["inline::basic", "inline::llm-as-judge", "inline::braintrust"],
-        "tool_runtime": [
-            "remote::brave-search",
-            "remote::tavily-search",
-            "inline::rag-runtime",
-            "remote::model-context-protocol",
-        ],
-    }
-    name = "verification"
-
-    vector_io_providers = [
-        Provider(
-            provider_id="sqlite-vec",
-            provider_type="inline::sqlite-vec",
-            config=SQLiteVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
-        ),
-        Provider(
-            provider_id="${env.ENABLE_CHROMADB+chromadb}",
-            provider_type="remote::chromadb",
-            config=ChromaVectorIOConfig.sample_run_config(url="${env.CHROMADB_URL:}"),
-        ),
-        Provider(
-            provider_id="${env.ENABLE_PGVECTOR+pgvector}",
-            provider_type="remote::pgvector",
-            config=PGVectorVectorIOConfig.sample_run_config(
-                db="${env.PGVECTOR_DB:}",
-                user="${env.PGVECTOR_USER:}",
-                password="${env.PGVECTOR_PASSWORD:}",
-            ),
-        ),
-    ]
-    embedding_provider = Provider(
-        provider_id="sentence-transformers",
-        provider_type="inline::sentence-transformers",
-        config=SentenceTransformersInferenceConfig.sample_run_config(),
-    )
-
-    default_tool_groups = [
-        ToolGroupInput(
-            toolgroup_id="builtin::websearch",
-            provider_id="tavily-search",
-        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::rag",
-            provider_id="rag-runtime",
-        ),
-    ]
-    embedding_model = ModelInput(
-        model_id="all-MiniLM-L6-v2",
-        provider_id=embedding_provider.provider_id,
-        model_type=ModelType.embedding,
-        metadata={
-            "embedding_dimension": 384,
-        },
-    )
-
-    default_models = get_model_registry(available_models)
-    return DistributionTemplate(
-        name=name,
-        distro_type="self_hosted",
-        description="Distribution for running e2e tests in CI",
-        container_image=None,
-        template_path=None,
-        providers=providers,
-        available_models_by_provider=available_models,
-        run_configs={
-            "run.yaml": RunConfigSettings(
-                provider_overrides={
-                    "inference": inference_providers + [embedding_provider],
-                    "vector_io": vector_io_providers,
-                },
-                default_models=default_models + [embedding_model],
-                default_tool_groups=default_tool_groups,
-                default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
-            ),
-        },
-        run_config_env_vars={
-            "LLAMA_STACK_PORT": (
-                "8321",
-                "Port for the Llama Stack distribution server",
-            ),
-            "FIREWORKS_API_KEY": (
-                "",
-                "Fireworks API Key",
-            ),
-            "OPENAI_API_KEY": (
-                "",
-                "OpenAI API Key",
-            ),
-        },
-    )
--- a/llama_stack/templates/vllm-gpu/build.yaml
+++ b/llama_stack/templates/vllm-gpu/build.yaml
@ -31,4 +31,5 @@ distribution_spec:
    - remote::model-context-protocol
 image_type: conda
 additional_pip_packages:
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/vllm-gpu/run.yaml
+++ b/llama_stack/templates/vllm-gpu/run.yaml
@ -52,7 +52,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/vllm-gpu}/trace_store.db
  eval:
--- a/llama_stack/templates/watsonx/build.yaml
+++ b/llama_stack/templates/watsonx/build.yaml
@ -29,4 +29,5 @@ distribution_spec:
    - remote::model-context-protocol
 image_type: conda
 additional_pip_packages:
+- aiosqlite
 - sqlalchemy[asyncio]
--- a/llama_stack/templates/watsonx/run.yaml
+++ b/llama_stack/templates/watsonx/run.yaml
@ -49,7 +49,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
-      service_name: ${env.OTEL_SERVICE_NAME:}
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/watsonx}/trace_store.db
  eval: