chore: remove leftover llama_stack directory (#3940)

# What does this PR do?

Followup on https://github.com/llamastack/llama-stack/pull/3920 where
the llama_stack directory was moved under src.

Signed-off-by: Sébastien Han <seb@redhat.com>

llama_stack/distributions/ci-tests/build.yaml

@@ -1,59 +0,0 @@
-version: 2
-distribution_spec:
-  description: CI tests for Llama Stack
-  providers:
-    inference:
-    - provider_type: remote::cerebras
-    - provider_type: remote::ollama
-    - provider_type: remote::vllm
-    - provider_type: remote::tgi
-    - provider_type: remote::fireworks
-    - provider_type: remote::together
-    - provider_type: remote::bedrock
-    - provider_type: remote::nvidia
-    - provider_type: remote::openai
-    - provider_type: remote::anthropic
-    - provider_type: remote::gemini
-    - provider_type: remote::vertexai
-    - provider_type: remote::groq
-    - provider_type: remote::sambanova
-    - provider_type: remote::azure
-    - provider_type: inline::sentence-transformers
-    vector_io:
-    - provider_type: inline::faiss
-    - provider_type: inline::sqlite-vec
-    - provider_type: inline::milvus
-    - provider_type: remote::chromadb
-    - provider_type: remote::pgvector
-    - provider_type: remote::qdrant
-    - provider_type: remote::weaviate
-    files:
-    - provider_type: inline::localfs
-    safety:
-    - provider_type: inline::llama-guard
-    - provider_type: inline::code-scanner
-    agents:
-    - provider_type: inline::meta-reference
-    post_training:
-    - provider_type: inline::torchtune-cpu
-    eval:
-    - provider_type: inline::meta-reference
-    datasetio:
-    - provider_type: remote::huggingface
-    - provider_type: inline::localfs
-    scoring:
-    - provider_type: inline::basic
-    - provider_type: inline::llm-as-judge
-    - provider_type: inline::braintrust
-    tool_runtime:
-    - provider_type: remote::brave-search
-    - provider_type: remote::tavily-search
-    - provider_type: inline::rag-runtime
-    - provider_type: remote::model-context-protocol
-    batches:
-    - provider_type: inline::reference
-image_type: venv
-additional_pip_packages:
-- aiosqlite
-- asyncpg
-- sqlalchemy[asyncio]

llama_stack/distributions/ci-tests/run.yaml

@@ -1,281 +0,0 @@
-version: 2
-image_name: ci-tests
-apis:
-- agents
-- batches
-- datasetio
-- eval
-- files
-- inference
-- post_training
-- safety
-- scoring
-- tool_runtime
-- vector_io
-providers:
-  inference:
-  - provider_id: ${env.CEREBRAS_API_KEY:+cerebras}
-    provider_type: remote::cerebras
-    config:
-      base_url: https://api.cerebras.ai
-      api_key: ${env.CEREBRAS_API_KEY:=}
-  - provider_id: ${env.OLLAMA_URL:+ollama}
-    provider_type: remote::ollama
-    config:
-      url: ${env.OLLAMA_URL:=http://localhost:11434}
-  - provider_id: ${env.VLLM_URL:+vllm}
-    provider_type: remote::vllm
-    config:
-      url: ${env.VLLM_URL:=}
-      max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
-      api_token: ${env.VLLM_API_TOKEN:=fake}
-      tls_verify: ${env.VLLM_TLS_VERIFY:=true}
-  - provider_id: ${env.TGI_URL:+tgi}
-    provider_type: remote::tgi
-    config:
-      url: ${env.TGI_URL:=}
-  - provider_id: fireworks
-    provider_type: remote::fireworks
-    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: bedrock
-    provider_type: remote::bedrock
-  - provider_id: ${env.NVIDIA_API_KEY:+nvidia}
-    provider_type: remote::nvidia
-    config:
-      url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
-      api_key: ${env.NVIDIA_API_KEY:=}
-      append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
-  - provider_id: openai
-    provider_type: remote::openai
-    config:
-      api_key: ${env.OPENAI_API_KEY:=}
-      base_url: ${env.OPENAI_BASE_URL:=https://api.openai.com/v1}
-  - provider_id: anthropic
-    provider_type: remote::anthropic
-    config:
-      api_key: ${env.ANTHROPIC_API_KEY:=}
-  - provider_id: gemini
-    provider_type: remote::gemini
-    config:
-      api_key: ${env.GEMINI_API_KEY:=}
-  - provider_id: ${env.VERTEX_AI_PROJECT:+vertexai}
-    provider_type: remote::vertexai
-    config:
-      project: ${env.VERTEX_AI_PROJECT:=}
-      location: ${env.VERTEX_AI_LOCATION:=us-central1}
-  - provider_id: groq
-    provider_type: remote::groq
-    config:
-      url: https://api.groq.com
-      api_key: ${env.GROQ_API_KEY:=}
-  - provider_id: sambanova
-    provider_type: remote::sambanova
-    config:
-      url: https://api.sambanova.ai/v1
-      api_key: ${env.SAMBANOVA_API_KEY:=}
-  - provider_id: ${env.AZURE_API_KEY:+azure}
-    provider_type: remote::azure
-    config:
-      api_key: ${env.AZURE_API_KEY:=}
-      api_base: ${env.AZURE_API_BASE:=}
-      api_version: ${env.AZURE_API_VERSION:=}
-      api_type: ${env.AZURE_API_TYPE:=}
-  - provider_id: sentence-transformers
-    provider_type: inline::sentence-transformers
-  vector_io:
-  - provider_id: faiss
-    provider_type: inline::faiss
-    config:
-      persistence:
-        namespace: vector_io::faiss
-        backend: kv_default
-  - provider_id: sqlite-vec
-    provider_type: inline::sqlite-vec
-    config:
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/sqlite_vec.db
-      persistence:
-        namespace: vector_io::sqlite_vec
-        backend: kv_default
-  - provider_id: ${env.MILVUS_URL:+milvus}
-    provider_type: inline::milvus
-    config:
-      db_path: ${env.MILVUS_DB_PATH:=~/.llama/distributions/ci-tests}/milvus.db
-      persistence:
-        namespace: vector_io::milvus
-        backend: kv_default
-  - provider_id: ${env.CHROMADB_URL:+chromadb}
-    provider_type: remote::chromadb
-    config:
-      url: ${env.CHROMADB_URL:=}
-      persistence:
-        namespace: vector_io::chroma_remote
-        backend: kv_default
-  - provider_id: ${env.PGVECTOR_DB:+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:=}
-      persistence:
-        namespace: vector_io::pgvector
-        backend: kv_default
-  - provider_id: ${env.QDRANT_URL:+qdrant}
-    provider_type: remote::qdrant
-    config:
-      api_key: ${env.QDRANT_API_KEY:=}
-      persistence:
-        namespace: vector_io::qdrant_remote
-        backend: kv_default
-  - provider_id: ${env.WEAVIATE_CLUSTER_URL:+weaviate}
-    provider_type: remote::weaviate
-    config:
-      weaviate_api_key: null
-      weaviate_cluster_url: ${env.WEAVIATE_CLUSTER_URL:=localhost:8080}
-      persistence:
-        namespace: vector_io::weaviate
-        backend: kv_default
-  files:
-  - provider_id: meta-reference-files
-    provider_type: inline::localfs
-    config:
-      storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/ci-tests/files}
-      metadata_store:
-        table_name: files_metadata
-        backend: sql_default
-  safety:
-  - provider_id: llama-guard
-    provider_type: inline::llama-guard
-    config:
-      excluded_categories: []
-  - provider_id: code-scanner
-    provider_type: inline::code-scanner
-  agents:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      persistence:
-        agent_state:
-          namespace: agents
-          backend: kv_default
-        responses:
-          table_name: responses
-          backend: sql_default
-          max_write_queue_size: 10000
-          num_writers: 4
-  post_training:
-  - provider_id: torchtune-cpu
-    provider_type: inline::torchtune-cpu
-    config:
-      checkpoint_format: meta
-  eval:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      kvstore:
-        namespace: eval
-        backend: kv_default
-  datasetio:
-  - provider_id: huggingface
-    provider_type: remote::huggingface
-    config:
-      kvstore:
-        namespace: datasetio::huggingface
-        backend: kv_default
-  - provider_id: localfs
-    provider_type: inline::localfs
-    config:
-      kvstore:
-        namespace: datasetio::localfs
-        backend: kv_default
-  scoring:
-  - provider_id: basic
-    provider_type: inline::basic
-  - provider_id: llm-as-judge
-    provider_type: inline::llm-as-judge
-  - 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
-  - provider_id: model-context-protocol
-    provider_type: remote::model-context-protocol
-  batches:
-  - provider_id: reference
-    provider_type: inline::reference
-    config:
-      kvstore:
-        namespace: batches
-        backend: kv_default
-storage:
-  backends:
-    kv_default:
-      type: kv_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/kvstore.db
-    sql_default:
-      type: sql_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/sql_store.db
-  stores:
-    metadata:
-      namespace: registry
-      backend: kv_default
-    inference:
-      table_name: inference_store
-      backend: sql_default
-      max_write_queue_size: 10000
-      num_writers: 4
-    conversations:
-      table_name: openai_conversations
-      backend: sql_default
-    prompts:
-      namespace: prompts
-      backend: kv_default
-registered_resources:
-  models: []
-  shields:
-  - shield_id: llama-guard
-    provider_id: ${env.SAFETY_MODEL:+llama-guard}
-    provider_shield_id: ${env.SAFETY_MODEL:=}
-  - shield_id: code-scanner
-    provider_id: ${env.CODE_SCANNER_MODEL:+code-scanner}
-    provider_shield_id: ${env.CODE_SCANNER_MODEL:=}
-  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
-telemetry:
-  enabled: true
-vector_stores:
-  default_provider_id: faiss
-  default_embedding_model:
-    provider_id: sentence-transformers
-    model_id: nomic-ai/nomic-embed-text-v1.5
-safety:
-  default_shield_id: llama-guard

llama_stack/distributions/dell/build.yaml

@@ -1,33 +0,0 @@
-version: 2
-distribution_spec:
-  description: Dell's distribution of Llama Stack. TGI inference via Dell's custom
-    container
-  providers:
-    inference:
-    - provider_type: remote::tgi
-    - provider_type: inline::sentence-transformers
-    vector_io:
-    - provider_type: inline::faiss
-    - provider_type: remote::chromadb
-    - provider_type: remote::pgvector
-    safety:
-    - provider_type: inline::llama-guard
-    agents:
-    - provider_type: inline::meta-reference
-    eval:
-    - provider_type: inline::meta-reference
-    datasetio:
-    - provider_type: remote::huggingface
-    - provider_type: inline::localfs
-    scoring:
-    - provider_type: inline::basic
-    - provider_type: inline::llm-as-judge
-    - provider_type: inline::braintrust
-    tool_runtime:
-    - provider_type: remote::brave-search
-    - provider_type: remote::tavily-search
-    - provider_type: inline::rag-runtime
-image_type: venv
-additional_pip_packages:
-- aiosqlite
-- sqlalchemy[asyncio]

llama_stack/distributions/dell/run-with-safety.yaml

@@ -1,144 +0,0 @@
-version: 2
-image_name: dell
-apis:
-- agents
-- datasetio
-- eval
-- inference
-- safety
-- scoring
-- tool_runtime
-- vector_io
-providers:
-  inference:
-  - provider_id: tgi0
-    provider_type: remote::tgi
-    config:
-      url: ${env.DEH_URL}
-  - provider_id: tgi1
-    provider_type: remote::tgi
-    config:
-      url: ${env.DEH_SAFETY_URL}
-  - provider_id: sentence-transformers
-    provider_type: inline::sentence-transformers
-  vector_io:
-  - provider_id: chromadb
-    provider_type: remote::chromadb
-    config:
-      url: ${env.CHROMADB_URL:=}
-      persistence:
-        namespace: vector_io::chroma_remote
-        backend: kv_default
-  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:
-        agent_state:
-          namespace: agents
-          backend: kv_default
-        responses:
-          table_name: responses
-          backend: sql_default
-          max_write_queue_size: 10000
-          num_writers: 4
-  eval:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      kvstore:
-        namespace: eval
-        backend: kv_default
-  datasetio:
-  - provider_id: huggingface
-    provider_type: remote::huggingface
-    config:
-      kvstore:
-        namespace: datasetio::huggingface
-        backend: kv_default
-  - provider_id: localfs
-    provider_type: inline::localfs
-    config:
-      kvstore:
-        namespace: datasetio::localfs
-        backend: kv_default
-  scoring:
-  - provider_id: basic
-    provider_type: inline::basic
-  - provider_id: llm-as-judge
-    provider_type: inline::llm-as-judge
-  - 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
-storage:
-  backends:
-    kv_default:
-      type: kv_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/kvstore.db
-    sql_default:
-      type: sql_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/sql_store.db
-  stores:
-    metadata:
-      namespace: registry
-      backend: kv_default
-    inference:
-      table_name: inference_store
-      backend: sql_default
-      max_write_queue_size: 10000
-      num_writers: 4
-    conversations:
-      table_name: openai_conversations
-      backend: sql_default
-    prompts:
-      namespace: prompts
-      backend: kv_default
-registered_resources:
-  models:
-  - metadata: {}
-    model_id: ${env.INFERENCE_MODEL}
-    provider_id: tgi0
-    model_type: llm
-  - metadata: {}
-    model_id: ${env.SAFETY_MODEL}
-    provider_id: tgi1
-    model_type: llm
-  - metadata:
-      embedding_dimension: 768
-    model_id: nomic-embed-text-v1.5
-    provider_id: sentence-transformers
-    model_type: embedding
-  shields:
-  - shield_id: ${env.SAFETY_MODEL}
-  vector_dbs: []
-  datasets: []
-  scoring_fns: []
-  benchmarks: []
-  tool_groups:
-  - toolgroup_id: builtin::websearch
-    provider_id: brave-search
-  - toolgroup_id: builtin::rag
-    provider_id: rag-runtime
-server:
-  port: 8321
-telemetry:
-  enabled: true

llama_stack/distributions/dell/run.yaml

@@ -1,135 +0,0 @@
-version: 2
-image_name: dell
-apis:
-- agents
-- datasetio
-- eval
-- inference
-- safety
-- scoring
-- tool_runtime
-- vector_io
-providers:
-  inference:
-  - provider_id: tgi0
-    provider_type: remote::tgi
-    config:
-      url: ${env.DEH_URL}
-  - provider_id: sentence-transformers
-    provider_type: inline::sentence-transformers
-  vector_io:
-  - provider_id: chromadb
-    provider_type: remote::chromadb
-    config:
-      url: ${env.CHROMADB_URL:=}
-      persistence:
-        namespace: vector_io::chroma_remote
-        backend: kv_default
-  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:
-        agent_state:
-          namespace: agents
-          backend: kv_default
-        responses:
-          table_name: responses
-          backend: sql_default
-          max_write_queue_size: 10000
-          num_writers: 4
-  eval:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      kvstore:
-        namespace: eval
-        backend: kv_default
-  datasetio:
-  - provider_id: huggingface
-    provider_type: remote::huggingface
-    config:
-      kvstore:
-        namespace: datasetio::huggingface
-        backend: kv_default
-  - provider_id: localfs
-    provider_type: inline::localfs
-    config:
-      kvstore:
-        namespace: datasetio::localfs
-        backend: kv_default
-  scoring:
-  - provider_id: basic
-    provider_type: inline::basic
-  - provider_id: llm-as-judge
-    provider_type: inline::llm-as-judge
-  - 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
-storage:
-  backends:
-    kv_default:
-      type: kv_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/kvstore.db
-    sql_default:
-      type: sql_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/sql_store.db
-  stores:
-    metadata:
-      namespace: registry
-      backend: kv_default
-    inference:
-      table_name: inference_store
-      backend: sql_default
-      max_write_queue_size: 10000
-      num_writers: 4
-    conversations:
-      table_name: openai_conversations
-      backend: sql_default
-    prompts:
-      namespace: prompts
-      backend: kv_default
-registered_resources:
-  models:
-  - metadata: {}
-    model_id: ${env.INFERENCE_MODEL}
-    provider_id: tgi0
-    model_type: llm
-  - metadata:
-      embedding_dimension: 768
-    model_id: nomic-embed-text-v1.5
-    provider_id: sentence-transformers
-    model_type: embedding
-  shields: []
-  vector_dbs: []
-  datasets: []
-  scoring_fns: []
-  benchmarks: []
-  tool_groups:
-  - toolgroup_id: builtin::websearch
-    provider_id: brave-search
-  - toolgroup_id: builtin::rag
-    provider_id: rag-runtime
-server:
-  port: 8321
-telemetry:
-  enabled: true

llama_stack/distributions/meta-reference-gpu/build.yaml

@@ -1,32 +0,0 @@
-version: 2
-distribution_spec:
-  description: Use Meta Reference for running LLM inference
-  providers:
-    inference:
-    - provider_type: inline::meta-reference
-    vector_io:
-    - provider_type: inline::faiss
-    - provider_type: remote::chromadb
-    - provider_type: remote::pgvector
-    safety:
-    - provider_type: inline::llama-guard
-    agents:
-    - provider_type: inline::meta-reference
-    eval:
-    - provider_type: inline::meta-reference
-    datasetio:
-    - provider_type: remote::huggingface
-    - provider_type: inline::localfs
-    scoring:
-    - provider_type: inline::basic
-    - provider_type: inline::llm-as-judge
-    - provider_type: inline::braintrust
-    tool_runtime:
-    - provider_type: remote::brave-search
-    - provider_type: remote::tavily-search
-    - provider_type: inline::rag-runtime
-    - provider_type: remote::model-context-protocol
-image_type: venv
-additional_pip_packages:
-- aiosqlite
-- sqlalchemy[asyncio]

llama_stack/distributions/meta-reference-gpu/run-with-safety.yaml

@@ -1,157 +0,0 @@
-version: 2
-image_name: meta-reference-gpu
-apis:
-- agents
-- datasetio
-- eval
-- inference
-- safety
-- scoring
-- tool_runtime
-- vector_io
-providers:
-  inference:
-  - provider_id: meta-reference-inference
-    provider_type: inline::meta-reference
-    config:
-      model: ${env.INFERENCE_MODEL}
-      checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:=null}
-      quantization:
-        type: ${env.QUANTIZATION_TYPE:=bf16}
-      model_parallel_size: ${env.MODEL_PARALLEL_SIZE:=0}
-      max_batch_size: ${env.MAX_BATCH_SIZE:=1}
-      max_seq_len: ${env.MAX_SEQ_LEN:=4096}
-  - provider_id: sentence-transformers
-    provider_type: inline::sentence-transformers
-  - provider_id: meta-reference-safety
-    provider_type: inline::meta-reference
-    config:
-      model: ${env.SAFETY_MODEL}
-      checkpoint_dir: ${env.SAFETY_CHECKPOINT_DIR:=null}
-      quantization:
-        type: ${env.QUANTIZATION_TYPE:=bf16}
-      model_parallel_size: ${env.MODEL_PARALLEL_SIZE:=0}
-      max_batch_size: ${env.MAX_BATCH_SIZE:=1}
-      max_seq_len: ${env.MAX_SEQ_LEN:=4096}
-  vector_io:
-  - provider_id: faiss
-    provider_type: inline::faiss
-    config:
-      persistence:
-        namespace: vector_io::faiss
-        backend: kv_default
-  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:
-        agent_state:
-          namespace: agents
-          backend: kv_default
-        responses:
-          table_name: responses
-          backend: sql_default
-          max_write_queue_size: 10000
-          num_writers: 4
-  eval:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      kvstore:
-        namespace: eval
-        backend: kv_default
-  datasetio:
-  - provider_id: huggingface
-    provider_type: remote::huggingface
-    config:
-      kvstore:
-        namespace: datasetio::huggingface
-        backend: kv_default
-  - provider_id: localfs
-    provider_type: inline::localfs
-    config:
-      kvstore:
-        namespace: datasetio::localfs
-        backend: kv_default
-  scoring:
-  - provider_id: basic
-    provider_type: inline::basic
-  - provider_id: llm-as-judge
-    provider_type: inline::llm-as-judge
-  - 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
-  - provider_id: model-context-protocol
-    provider_type: remote::model-context-protocol
-storage:
-  backends:
-    kv_default:
-      type: kv_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/kvstore.db
-    sql_default:
-      type: sql_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/sql_store.db
-  stores:
-    metadata:
-      namespace: registry
-      backend: kv_default
-    inference:
-      table_name: inference_store
-      backend: sql_default
-      max_write_queue_size: 10000
-      num_writers: 4
-    conversations:
-      table_name: openai_conversations
-      backend: sql_default
-    prompts:
-      namespace: prompts
-      backend: kv_default
-registered_resources:
-  models:
-  - metadata: {}
-    model_id: ${env.INFERENCE_MODEL}
-    provider_id: meta-reference-inference
-    model_type: llm
-  - metadata: {}
-    model_id: ${env.SAFETY_MODEL}
-    provider_id: meta-reference-safety
-    model_type: llm
-  - metadata:
-      embedding_dimension: 768
-    model_id: nomic-embed-text-v1.5
-    provider_id: sentence-transformers
-    model_type: embedding
-  shields:
-  - shield_id: ${env.SAFETY_MODEL}
-  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
-telemetry:
-  enabled: true

llama_stack/distributions/meta-reference-gpu/run.yaml

@@ -1,142 +0,0 @@
-version: 2
-image_name: meta-reference-gpu
-apis:
-- agents
-- datasetio
-- eval
-- inference
-- safety
-- scoring
-- tool_runtime
-- vector_io
-providers:
-  inference:
-  - provider_id: meta-reference-inference
-    provider_type: inline::meta-reference
-    config:
-      model: ${env.INFERENCE_MODEL}
-      checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:=null}
-      quantization:
-        type: ${env.QUANTIZATION_TYPE:=bf16}
-      model_parallel_size: ${env.MODEL_PARALLEL_SIZE:=0}
-      max_batch_size: ${env.MAX_BATCH_SIZE:=1}
-      max_seq_len: ${env.MAX_SEQ_LEN:=4096}
-  - provider_id: sentence-transformers
-    provider_type: inline::sentence-transformers
-  vector_io:
-  - provider_id: faiss
-    provider_type: inline::faiss
-    config:
-      persistence:
-        namespace: vector_io::faiss
-        backend: kv_default
-  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:
-        agent_state:
-          namespace: agents
-          backend: kv_default
-        responses:
-          table_name: responses
-          backend: sql_default
-          max_write_queue_size: 10000
-          num_writers: 4
-  eval:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      kvstore:
-        namespace: eval
-        backend: kv_default
-  datasetio:
-  - provider_id: huggingface
-    provider_type: remote::huggingface
-    config:
-      kvstore:
-        namespace: datasetio::huggingface
-        backend: kv_default
-  - provider_id: localfs
-    provider_type: inline::localfs
-    config:
-      kvstore:
-        namespace: datasetio::localfs
-        backend: kv_default
-  scoring:
-  - provider_id: basic
-    provider_type: inline::basic
-  - provider_id: llm-as-judge
-    provider_type: inline::llm-as-judge
-  - 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
-  - provider_id: model-context-protocol
-    provider_type: remote::model-context-protocol
-storage:
-  backends:
-    kv_default:
-      type: kv_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/kvstore.db
-    sql_default:
-      type: sql_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/sql_store.db
-  stores:
-    metadata:
-      namespace: registry
-      backend: kv_default
-    inference:
-      table_name: inference_store
-      backend: sql_default
-      max_write_queue_size: 10000
-      num_writers: 4
-    conversations:
-      table_name: openai_conversations
-      backend: sql_default
-    prompts:
-      namespace: prompts
-      backend: kv_default
-registered_resources:
-  models:
-  - metadata: {}
-    model_id: ${env.INFERENCE_MODEL}
-    provider_id: meta-reference-inference
-    model_type: llm
-  - metadata:
-      embedding_dimension: 768
-    model_id: nomic-embed-text-v1.5
-    provider_id: sentence-transformers
-    model_type: embedding
-  shields: []
-  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
-telemetry:
-  enabled: true

llama_stack/distributions/nvidia/build.yaml

@@ -1,29 +0,0 @@
-version: 2
-distribution_spec:
-  description: Use NVIDIA NIM for running LLM inference, evaluation and safety
-  providers:
-    inference:
-    - provider_type: remote::nvidia
-    vector_io:
-    - provider_type: inline::faiss
-    safety:
-    - provider_type: remote::nvidia
-    agents:
-    - provider_type: inline::meta-reference
-    eval:
-    - provider_type: remote::nvidia
-    post_training:
-    - provider_type: remote::nvidia
-    datasetio:
-    - provider_type: inline::localfs
-    - provider_type: remote::nvidia
-    scoring:
-    - provider_type: inline::basic
-    tool_runtime:
-    - provider_type: inline::rag-runtime
-    files:
-    - provider_type: inline::localfs
-image_type: venv
-additional_pip_packages:
-- aiosqlite
-- sqlalchemy[asyncio]

llama_stack/distributions/nvidia/run-with-safety.yaml

@@ -1,140 +0,0 @@
-version: 2
-image_name: nvidia
-apis:
-- agents
-- datasetio
-- eval
-- files
-- inference
-- post_training
-- safety
-- scoring
-- tool_runtime
-- vector_io
-providers:
-  inference:
-  - provider_id: nvidia
-    provider_type: remote::nvidia
-    config:
-      url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
-      api_key: ${env.NVIDIA_API_KEY:=}
-      append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
-  - provider_id: nvidia
-    provider_type: remote::nvidia
-    config:
-      guardrails_service_url: ${env.GUARDRAILS_SERVICE_URL:=http://localhost:7331}
-      config_id: ${env.NVIDIA_GUARDRAILS_CONFIG_ID:=self-check}
-  vector_io:
-  - provider_id: faiss
-    provider_type: inline::faiss
-    config:
-      persistence:
-        namespace: vector_io::faiss
-        backend: kv_default
-  safety:
-  - provider_id: nvidia
-    provider_type: remote::nvidia
-    config:
-      guardrails_service_url: ${env.GUARDRAILS_SERVICE_URL:=http://localhost:7331}
-      config_id: ${env.NVIDIA_GUARDRAILS_CONFIG_ID:=self-check}
-  agents:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      persistence:
-        agent_state:
-          namespace: agents
-          backend: kv_default
-        responses:
-          table_name: responses
-          backend: sql_default
-          max_write_queue_size: 10000
-          num_writers: 4
-  eval:
-  - provider_id: nvidia
-    provider_type: remote::nvidia
-    config:
-      evaluator_url: ${env.NVIDIA_EVALUATOR_URL:=http://localhost:7331}
-  post_training:
-  - provider_id: nvidia
-    provider_type: remote::nvidia
-    config:
-      api_key: ${env.NVIDIA_API_KEY:=}
-      dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:=default}
-      project_id: ${env.NVIDIA_PROJECT_ID:=test-project}
-      customizer_url: ${env.NVIDIA_CUSTOMIZER_URL:=http://nemo.test}
-  datasetio:
-  - provider_id: localfs
-    provider_type: inline::localfs
-    config:
-      kvstore:
-        namespace: datasetio::localfs
-        backend: kv_default
-  - provider_id: nvidia
-    provider_type: remote::nvidia
-    config:
-      api_key: ${env.NVIDIA_API_KEY:=}
-      dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:=default}
-      project_id: ${env.NVIDIA_PROJECT_ID:=test-project}
-      datasets_url: ${env.NVIDIA_DATASETS_URL:=http://nemo.test}
-  scoring:
-  - provider_id: basic
-    provider_type: inline::basic
-  tool_runtime:
-  - provider_id: rag-runtime
-    provider_type: inline::rag-runtime
-  files:
-  - provider_id: meta-reference-files
-    provider_type: inline::localfs
-    config:
-      storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/nvidia/files}
-      metadata_store:
-        table_name: files_metadata
-        backend: sql_default
-storage:
-  backends:
-    kv_default:
-      type: kv_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/kvstore.db
-    sql_default:
-      type: sql_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/sql_store.db
-  stores:
-    metadata:
-      namespace: registry
-      backend: kv_default
-    inference:
-      table_name: inference_store
-      backend: sql_default
-      max_write_queue_size: 10000
-      num_writers: 4
-    conversations:
-      table_name: openai_conversations
-      backend: sql_default
-    prompts:
-      namespace: prompts
-      backend: kv_default
-registered_resources:
-  models:
-  - metadata: {}
-    model_id: ${env.INFERENCE_MODEL}
-    provider_id: nvidia
-    model_type: llm
-  - metadata: {}
-    model_id: ${env.SAFETY_MODEL}
-    provider_id: nvidia
-    model_type: llm
-  shields:
-  - shield_id: ${env.SAFETY_MODEL}
-    provider_id: nvidia
-  vector_dbs: []
-  datasets: []
-  scoring_fns: []
-  benchmarks: []
-  tool_groups:
-  - toolgroup_id: builtin::rag
-    provider_id: rag-runtime
-server:
-  port: 8321
-telemetry:
-  enabled: true

llama_stack/distributions/nvidia/run.yaml

@@ -1,119 +0,0 @@
-version: 2
-image_name: nvidia
-apis:
-- agents
-- datasetio
-- eval
-- files
-- inference
-- post_training
-- safety
-- scoring
-- tool_runtime
-- vector_io
-providers:
-  inference:
-  - provider_id: nvidia
-    provider_type: remote::nvidia
-    config:
-      url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
-      api_key: ${env.NVIDIA_API_KEY:=}
-      append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
-  vector_io:
-  - provider_id: faiss
-    provider_type: inline::faiss
-    config:
-      persistence:
-        namespace: vector_io::faiss
-        backend: kv_default
-  safety:
-  - provider_id: nvidia
-    provider_type: remote::nvidia
-    config:
-      guardrails_service_url: ${env.GUARDRAILS_SERVICE_URL:=http://localhost:7331}
-      config_id: ${env.NVIDIA_GUARDRAILS_CONFIG_ID:=self-check}
-  agents:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      persistence:
-        agent_state:
-          namespace: agents
-          backend: kv_default
-        responses:
-          table_name: responses
-          backend: sql_default
-          max_write_queue_size: 10000
-          num_writers: 4
-  eval:
-  - provider_id: nvidia
-    provider_type: remote::nvidia
-    config:
-      evaluator_url: ${env.NVIDIA_EVALUATOR_URL:=http://localhost:7331}
-  post_training:
-  - provider_id: nvidia
-    provider_type: remote::nvidia
-    config:
-      api_key: ${env.NVIDIA_API_KEY:=}
-      dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:=default}
-      project_id: ${env.NVIDIA_PROJECT_ID:=test-project}
-      customizer_url: ${env.NVIDIA_CUSTOMIZER_URL:=http://nemo.test}
-  datasetio:
-  - provider_id: nvidia
-    provider_type: remote::nvidia
-    config:
-      api_key: ${env.NVIDIA_API_KEY:=}
-      dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:=default}
-      project_id: ${env.NVIDIA_PROJECT_ID:=test-project}
-      datasets_url: ${env.NVIDIA_DATASETS_URL:=http://nemo.test}
-  scoring:
-  - provider_id: basic
-    provider_type: inline::basic
-  tool_runtime:
-  - provider_id: rag-runtime
-    provider_type: inline::rag-runtime
-  files:
-  - provider_id: meta-reference-files
-    provider_type: inline::localfs
-    config:
-      storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/nvidia/files}
-      metadata_store:
-        table_name: files_metadata
-        backend: sql_default
-storage:
-  backends:
-    kv_default:
-      type: kv_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/kvstore.db
-    sql_default:
-      type: sql_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/sql_store.db
-  stores:
-    metadata:
-      namespace: registry
-      backend: kv_default
-    inference:
-      table_name: inference_store
-      backend: sql_default
-      max_write_queue_size: 10000
-      num_writers: 4
-    conversations:
-      table_name: openai_conversations
-      backend: sql_default
-    prompts:
-      namespace: prompts
-      backend: kv_default
-registered_resources:
-  models: []
-  shields: []
-  vector_dbs: []
-  datasets: []
-  scoring_fns: []
-  benchmarks: []
-  tool_groups:
-  - toolgroup_id: builtin::rag
-    provider_id: rag-runtime
-server:
-  port: 8321
-telemetry:
-  enabled: true

llama_stack/distributions/open-benchmark/build.yaml

@@ -1,36 +0,0 @@
-version: 2
-distribution_spec:
-  description: Distribution for running open benchmarks
-  providers:
-    inference:
-    - provider_type: remote::openai
-    - provider_type: remote::anthropic
-    - provider_type: remote::gemini
-    - provider_type: remote::groq
-    - provider_type: remote::together
-    vector_io:
-    - provider_type: inline::sqlite-vec
-    - provider_type: remote::chromadb
-    - provider_type: remote::pgvector
-    safety:
-    - provider_type: inline::llama-guard
-    agents:
-    - provider_type: inline::meta-reference
-    eval:
-    - provider_type: inline::meta-reference
-    datasetio:
-    - provider_type: remote::huggingface
-    - provider_type: inline::localfs
-    scoring:
-    - provider_type: inline::basic
-    - provider_type: inline::llm-as-judge
-    - provider_type: inline::braintrust
-    tool_runtime:
-    - provider_type: remote::brave-search
-    - provider_type: remote::tavily-search
-    - provider_type: inline::rag-runtime
-    - provider_type: remote::model-context-protocol
-image_type: venv
-additional_pip_packages:
-- aiosqlite
-- sqlalchemy[asyncio]

llama_stack/distributions/open-benchmark/run.yaml

@@ -1,255 +0,0 @@
-version: 2
-image_name: open-benchmark
-apis:
-- agents
-- datasetio
-- eval
-- inference
-- safety
-- scoring
-- tool_runtime
-- vector_io
-providers:
-  inference:
-  - provider_id: openai
-    provider_type: remote::openai
-    config:
-      api_key: ${env.OPENAI_API_KEY:=}
-      base_url: ${env.OPENAI_BASE_URL:=https://api.openai.com/v1}
-  - provider_id: anthropic
-    provider_type: remote::anthropic
-    config:
-      api_key: ${env.ANTHROPIC_API_KEY:=}
-  - provider_id: gemini
-    provider_type: remote::gemini
-    config:
-      api_key: ${env.GEMINI_API_KEY:=}
-  - provider_id: groq
-    provider_type: remote::groq
-    config:
-      url: https://api.groq.com
-      api_key: ${env.GROQ_API_KEY:=}
-  - provider_id: together
-    provider_type: remote::together
-    config:
-      url: https://api.together.xyz/v1
-      api_key: ${env.TOGETHER_API_KEY:=}
-  vector_io:
-  - provider_id: sqlite-vec
-    provider_type: inline::sqlite-vec
-    config:
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/sqlite_vec.db
-      persistence:
-        namespace: vector_io::sqlite_vec
-        backend: kv_default
-  - provider_id: ${env.ENABLE_CHROMADB:+chromadb}
-    provider_type: remote::chromadb
-    config:
-      url: ${env.CHROMADB_URL:=}
-      persistence:
-        namespace: vector_io::chroma_remote
-        backend: kv_default
-  - 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:=}
-      persistence:
-        namespace: vector_io::pgvector
-        backend: kv_default
-  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:
-        agent_state:
-          namespace: agents
-          backend: kv_default
-        responses:
-          table_name: responses
-          backend: sql_default
-          max_write_queue_size: 10000
-          num_writers: 4
-  eval:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      kvstore:
-        namespace: eval
-        backend: kv_default
-  datasetio:
-  - provider_id: huggingface
-    provider_type: remote::huggingface
-    config:
-      kvstore:
-        namespace: datasetio::huggingface
-        backend: kv_default
-  - provider_id: localfs
-    provider_type: inline::localfs
-    config:
-      kvstore:
-        namespace: datasetio::localfs
-        backend: kv_default
-  scoring:
-  - provider_id: basic
-    provider_type: inline::basic
-  - provider_id: llm-as-judge
-    provider_type: inline::llm-as-judge
-  - 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
-  - provider_id: model-context-protocol
-    provider_type: remote::model-context-protocol
-storage:
-  backends:
-    kv_default:
-      type: kv_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/kvstore.db
-    sql_default:
-      type: sql_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/sql_store.db
-  stores:
-    metadata:
-      namespace: registry
-      backend: kv_default
-    inference:
-      table_name: inference_store
-      backend: sql_default
-      max_write_queue_size: 10000
-      num_writers: 4
-    conversations:
-      table_name: openai_conversations
-      backend: sql_default
-    prompts:
-      namespace: prompts
-      backend: kv_default
-registered_resources:
-  models:
-  - metadata: {}
-    model_id: gpt-4o
-    provider_id: openai
-    provider_model_id: gpt-4o
-    model_type: llm
-  - metadata: {}
-    model_id: claude-3-5-sonnet-latest
-    provider_id: anthropic
-    provider_model_id: claude-3-5-sonnet-latest
-    model_type: llm
-  - metadata: {}
-    model_id: gemini/gemini-1.5-flash
-    provider_id: gemini
-    provider_model_id: gemini/gemini-1.5-flash
-    model_type: llm
-  - metadata: {}
-    model_id: meta-llama/Llama-3.3-70B-Instruct
-    provider_id: groq
-    provider_model_id: groq/llama-3.3-70b-versatile
-    model_type: llm
-  - metadata: {}
-    model_id: meta-llama/Llama-3.1-405B-Instruct
-    provider_id: together
-    provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
-    model_type: llm
-  shields:
-  - shield_id: meta-llama/Llama-Guard-3-8B
-  vector_dbs: []
-  datasets:
-  - purpose: eval/messages-answer
-    source:
-      type: uri
-      uri: huggingface://datasets/llamastack/simpleqa?split=train
-    metadata: {}
-    dataset_id: simpleqa
-  - purpose: eval/messages-answer
-    source:
-      type: uri
-      uri: huggingface://datasets/llamastack/mmlu_cot?split=test&name=all
-    metadata: {}
-    dataset_id: mmlu_cot
-  - purpose: eval/messages-answer
-    source:
-      type: uri
-      uri: huggingface://datasets/llamastack/gpqa_0shot_cot?split=test&name=gpqa_main
-    metadata: {}
-    dataset_id: gpqa_cot
-  - purpose: eval/messages-answer
-    source:
-      type: uri
-      uri: huggingface://datasets/llamastack/math_500?split=test
-    metadata: {}
-    dataset_id: math_500
-  - purpose: eval/messages-answer
-    source:
-      type: uri
-      uri: huggingface://datasets/llamastack/IfEval?split=train
-    metadata: {}
-    dataset_id: ifeval
-  - purpose: eval/messages-answer
-    source:
-      type: uri
-      uri: huggingface://datasets/llamastack/docvqa?split=val
-    metadata: {}
-    dataset_id: docvqa
-  scoring_fns: []
-  benchmarks:
-  - dataset_id: simpleqa
-    scoring_functions:
-    - llm-as-judge::405b-simpleqa
-    metadata: {}
-    benchmark_id: meta-reference-simpleqa
-  - dataset_id: mmlu_cot
-    scoring_functions:
-    - basic::regex_parser_multiple_choice_answer
-    metadata: {}
-    benchmark_id: meta-reference-mmlu-cot
-  - dataset_id: gpqa_cot
-    scoring_functions:
-    - basic::regex_parser_multiple_choice_answer
-    metadata: {}
-    benchmark_id: meta-reference-gpqa-cot
-  - dataset_id: math_500
-    scoring_functions:
-    - basic::regex_parser_math_response
-    metadata: {}
-    benchmark_id: meta-reference-math-500
-  - dataset_id: ifeval
-    scoring_functions:
-    - basic::ifeval
-    metadata: {}
-    benchmark_id: meta-reference-ifeval
-  - dataset_id: docvqa
-    scoring_functions:
-    - basic::docvqa
-    metadata: {}
-    benchmark_id: meta-reference-docvqa
-  tool_groups:
-  - toolgroup_id: builtin::websearch
-    provider_id: tavily-search
-  - toolgroup_id: builtin::rag
-    provider_id: rag-runtime
-server:
-  port: 8321
-telemetry:
-  enabled: true

llama_stack/distributions/postgres-demo/build.yaml

@@ -1,23 +0,0 @@
-version: 2
-distribution_spec:
-  description: Quick start template for running Llama Stack with several popular providers
-  providers:
-    inference:
-    - provider_type: remote::vllm
-    - provider_type: inline::sentence-transformers
-    vector_io:
-    - provider_type: remote::chromadb
-    safety:
-    - provider_type: inline::llama-guard
-    agents:
-    - provider_type: inline::meta-reference
-    tool_runtime:
-    - provider_type: remote::brave-search
-    - provider_type: remote::tavily-search
-    - provider_type: inline::rag-runtime
-    - provider_type: remote::model-context-protocol
-image_type: venv
-additional_pip_packages:
-- asyncpg
-- psycopg2-binary
-- sqlalchemy[asyncio]

llama_stack/distributions/postgres-demo/run.yaml

@@ -1,118 +0,0 @@
-version: 2
-image_name: postgres-demo
-apis:
-- agents
-- inference
-- safety
-- 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
-  vector_io:
-  - provider_id: ${env.ENABLE_CHROMADB:+chromadb}
-    provider_type: remote::chromadb
-    config:
-      url: ${env.CHROMADB_URL:=}
-      persistence:
-        namespace: vector_io::chroma_remote
-        backend: kv_default
-  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:
-        agent_state:
-          namespace: agents
-          backend: kv_default
-        responses:
-          table_name: responses
-          backend: sql_default
-          max_write_queue_size: 10000
-          num_writers: 4
-  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
-  - provider_id: model-context-protocol
-    provider_type: remote::model-context-protocol
-storage:
-  backends:
-    kv_default:
-      type: kv_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}
-    sql_default:
-      type: sql_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}
-  stores:
-    metadata:
-      namespace: registry
-      backend: kv_default
-    inference:
-      table_name: inference_store
-      backend: sql_default
-      max_write_queue_size: 10000
-      num_writers: 4
-    conversations:
-      table_name: openai_conversations
-      backend: sql_default
-    prompts:
-      namespace: prompts
-      backend: kv_default
-registered_resources:
-  models:
-  - metadata: {}
-    model_id: ${env.INFERENCE_MODEL}
-    provider_id: vllm-inference
-    model_type: llm
-  - metadata:
-      embedding_dimension: 768
-    model_id: nomic-embed-text-v1.5
-    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
-telemetry:
-  enabled: true

llama_stack/distributions/starter-gpu/build.yaml

@@ -1,60 +0,0 @@
-version: 2
-distribution_spec:
-  description: Quick start template for running Llama Stack with several popular providers.
-    This distribution is intended for GPU-enabled environments.
-  providers:
-    inference:
-    - provider_type: remote::cerebras
-    - provider_type: remote::ollama
-    - provider_type: remote::vllm
-    - provider_type: remote::tgi
-    - provider_type: remote::fireworks
-    - provider_type: remote::together
-    - provider_type: remote::bedrock
-    - provider_type: remote::nvidia
-    - provider_type: remote::openai
-    - provider_type: remote::anthropic
-    - provider_type: remote::gemini
-    - provider_type: remote::vertexai
-    - provider_type: remote::groq
-    - provider_type: remote::sambanova
-    - provider_type: remote::azure
-    - provider_type: inline::sentence-transformers
-    vector_io:
-    - provider_type: inline::faiss
-    - provider_type: inline::sqlite-vec
-    - provider_type: inline::milvus
-    - provider_type: remote::chromadb
-    - provider_type: remote::pgvector
-    - provider_type: remote::qdrant
-    - provider_type: remote::weaviate
-    files:
-    - provider_type: inline::localfs
-    safety:
-    - provider_type: inline::llama-guard
-    - provider_type: inline::code-scanner
-    agents:
-    - provider_type: inline::meta-reference
-    post_training:
-    - provider_type: inline::huggingface-gpu
-    eval:
-    - provider_type: inline::meta-reference
-    datasetio:
-    - provider_type: remote::huggingface
-    - provider_type: inline::localfs
-    scoring:
-    - provider_type: inline::basic
-    - provider_type: inline::llm-as-judge
-    - provider_type: inline::braintrust
-    tool_runtime:
-    - provider_type: remote::brave-search
-    - provider_type: remote::tavily-search
-    - provider_type: inline::rag-runtime
-    - provider_type: remote::model-context-protocol
-    batches:
-    - provider_type: inline::reference
-image_type: venv
-additional_pip_packages:
-- aiosqlite
-- asyncpg
-- sqlalchemy[asyncio]

llama_stack/distributions/starter-gpu/run.yaml

@@ -1,284 +0,0 @@
-version: 2
-image_name: starter-gpu
-apis:
-- agents
-- batches
-- datasetio
-- eval
-- files
-- inference
-- post_training
-- safety
-- scoring
-- tool_runtime
-- vector_io
-providers:
-  inference:
-  - provider_id: ${env.CEREBRAS_API_KEY:+cerebras}
-    provider_type: remote::cerebras
-    config:
-      base_url: https://api.cerebras.ai
-      api_key: ${env.CEREBRAS_API_KEY:=}
-  - provider_id: ${env.OLLAMA_URL:+ollama}
-    provider_type: remote::ollama
-    config:
-      url: ${env.OLLAMA_URL:=http://localhost:11434}
-  - provider_id: ${env.VLLM_URL:+vllm}
-    provider_type: remote::vllm
-    config:
-      url: ${env.VLLM_URL:=}
-      max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
-      api_token: ${env.VLLM_API_TOKEN:=fake}
-      tls_verify: ${env.VLLM_TLS_VERIFY:=true}
-  - provider_id: ${env.TGI_URL:+tgi}
-    provider_type: remote::tgi
-    config:
-      url: ${env.TGI_URL:=}
-  - provider_id: fireworks
-    provider_type: remote::fireworks
-    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: bedrock
-    provider_type: remote::bedrock
-  - provider_id: ${env.NVIDIA_API_KEY:+nvidia}
-    provider_type: remote::nvidia
-    config:
-      url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
-      api_key: ${env.NVIDIA_API_KEY:=}
-      append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
-  - provider_id: openai
-    provider_type: remote::openai
-    config:
-      api_key: ${env.OPENAI_API_KEY:=}
-      base_url: ${env.OPENAI_BASE_URL:=https://api.openai.com/v1}
-  - provider_id: anthropic
-    provider_type: remote::anthropic
-    config:
-      api_key: ${env.ANTHROPIC_API_KEY:=}
-  - provider_id: gemini
-    provider_type: remote::gemini
-    config:
-      api_key: ${env.GEMINI_API_KEY:=}
-  - provider_id: ${env.VERTEX_AI_PROJECT:+vertexai}
-    provider_type: remote::vertexai
-    config:
-      project: ${env.VERTEX_AI_PROJECT:=}
-      location: ${env.VERTEX_AI_LOCATION:=us-central1}
-  - provider_id: groq
-    provider_type: remote::groq
-    config:
-      url: https://api.groq.com
-      api_key: ${env.GROQ_API_KEY:=}
-  - provider_id: sambanova
-    provider_type: remote::sambanova
-    config:
-      url: https://api.sambanova.ai/v1
-      api_key: ${env.SAMBANOVA_API_KEY:=}
-  - provider_id: ${env.AZURE_API_KEY:+azure}
-    provider_type: remote::azure
-    config:
-      api_key: ${env.AZURE_API_KEY:=}
-      api_base: ${env.AZURE_API_BASE:=}
-      api_version: ${env.AZURE_API_VERSION:=}
-      api_type: ${env.AZURE_API_TYPE:=}
-  - provider_id: sentence-transformers
-    provider_type: inline::sentence-transformers
-  vector_io:
-  - provider_id: faiss
-    provider_type: inline::faiss
-    config:
-      persistence:
-        namespace: vector_io::faiss
-        backend: kv_default
-  - provider_id: sqlite-vec
-    provider_type: inline::sqlite-vec
-    config:
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/sqlite_vec.db
-      persistence:
-        namespace: vector_io::sqlite_vec
-        backend: kv_default
-  - provider_id: ${env.MILVUS_URL:+milvus}
-    provider_type: inline::milvus
-    config:
-      db_path: ${env.MILVUS_DB_PATH:=~/.llama/distributions/starter-gpu}/milvus.db
-      persistence:
-        namespace: vector_io::milvus
-        backend: kv_default
-  - provider_id: ${env.CHROMADB_URL:+chromadb}
-    provider_type: remote::chromadb
-    config:
-      url: ${env.CHROMADB_URL:=}
-      persistence:
-        namespace: vector_io::chroma_remote
-        backend: kv_default
-  - provider_id: ${env.PGVECTOR_DB:+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:=}
-      persistence:
-        namespace: vector_io::pgvector
-        backend: kv_default
-  - provider_id: ${env.QDRANT_URL:+qdrant}
-    provider_type: remote::qdrant
-    config:
-      api_key: ${env.QDRANT_API_KEY:=}
-      persistence:
-        namespace: vector_io::qdrant_remote
-        backend: kv_default
-  - provider_id: ${env.WEAVIATE_CLUSTER_URL:+weaviate}
-    provider_type: remote::weaviate
-    config:
-      weaviate_api_key: null
-      weaviate_cluster_url: ${env.WEAVIATE_CLUSTER_URL:=localhost:8080}
-      persistence:
-        namespace: vector_io::weaviate
-        backend: kv_default
-  files:
-  - provider_id: meta-reference-files
-    provider_type: inline::localfs
-    config:
-      storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter-gpu/files}
-      metadata_store:
-        table_name: files_metadata
-        backend: sql_default
-  safety:
-  - provider_id: llama-guard
-    provider_type: inline::llama-guard
-    config:
-      excluded_categories: []
-  - provider_id: code-scanner
-    provider_type: inline::code-scanner
-  agents:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      persistence:
-        agent_state:
-          namespace: agents
-          backend: kv_default
-        responses:
-          table_name: responses
-          backend: sql_default
-          max_write_queue_size: 10000
-          num_writers: 4
-  post_training:
-  - provider_id: huggingface-gpu
-    provider_type: inline::huggingface-gpu
-    config:
-      checkpoint_format: huggingface
-      distributed_backend: null
-      device: cpu
-      dpo_output_dir: ~/.llama/distributions/starter-gpu/dpo_output
-  eval:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      kvstore:
-        namespace: eval
-        backend: kv_default
-  datasetio:
-  - provider_id: huggingface
-    provider_type: remote::huggingface
-    config:
-      kvstore:
-        namespace: datasetio::huggingface
-        backend: kv_default
-  - provider_id: localfs
-    provider_type: inline::localfs
-    config:
-      kvstore:
-        namespace: datasetio::localfs
-        backend: kv_default
-  scoring:
-  - provider_id: basic
-    provider_type: inline::basic
-  - provider_id: llm-as-judge
-    provider_type: inline::llm-as-judge
-  - 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
-  - provider_id: model-context-protocol
-    provider_type: remote::model-context-protocol
-  batches:
-  - provider_id: reference
-    provider_type: inline::reference
-    config:
-      kvstore:
-        namespace: batches
-        backend: kv_default
-storage:
-  backends:
-    kv_default:
-      type: kv_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/kvstore.db
-    sql_default:
-      type: sql_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/sql_store.db
-  stores:
-    metadata:
-      namespace: registry
-      backend: kv_default
-    inference:
-      table_name: inference_store
-      backend: sql_default
-      max_write_queue_size: 10000
-      num_writers: 4
-    conversations:
-      table_name: openai_conversations
-      backend: sql_default
-    prompts:
-      namespace: prompts
-      backend: kv_default
-registered_resources:
-  models: []
-  shields:
-  - shield_id: llama-guard
-    provider_id: ${env.SAFETY_MODEL:+llama-guard}
-    provider_shield_id: ${env.SAFETY_MODEL:=}
-  - shield_id: code-scanner
-    provider_id: ${env.CODE_SCANNER_MODEL:+code-scanner}
-    provider_shield_id: ${env.CODE_SCANNER_MODEL:=}
-  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
-telemetry:
-  enabled: true
-vector_stores:
-  default_provider_id: faiss
-  default_embedding_model:
-    provider_id: sentence-transformers
-    model_id: nomic-ai/nomic-embed-text-v1.5
-safety:
-  default_shield_id: llama-guard

llama_stack/distributions/starter/build.yaml

@@ -1,60 +0,0 @@
-version: 2
-distribution_spec:
-  description: Quick start template for running Llama Stack with several popular providers.
-    This distribution is intended for CPU-only environments.
-  providers:
-    inference:
-    - provider_type: remote::cerebras
-    - provider_type: remote::ollama
-    - provider_type: remote::vllm
-    - provider_type: remote::tgi
-    - provider_type: remote::fireworks
-    - provider_type: remote::together
-    - provider_type: remote::bedrock
-    - provider_type: remote::nvidia
-    - provider_type: remote::openai
-    - provider_type: remote::anthropic
-    - provider_type: remote::gemini
-    - provider_type: remote::vertexai
-    - provider_type: remote::groq
-    - provider_type: remote::sambanova
-    - provider_type: remote::azure
-    - provider_type: inline::sentence-transformers
-    vector_io:
-    - provider_type: inline::faiss
-    - provider_type: inline::sqlite-vec
-    - provider_type: inline::milvus
-    - provider_type: remote::chromadb
-    - provider_type: remote::pgvector
-    - provider_type: remote::qdrant
-    - provider_type: remote::weaviate
-    files:
-    - provider_type: inline::localfs
-    safety:
-    - provider_type: inline::llama-guard
-    - provider_type: inline::code-scanner
-    agents:
-    - provider_type: inline::meta-reference
-    post_training:
-    - provider_type: inline::torchtune-cpu
-    eval:
-    - provider_type: inline::meta-reference
-    datasetio:
-    - provider_type: remote::huggingface
-    - provider_type: inline::localfs
-    scoring:
-    - provider_type: inline::basic
-    - provider_type: inline::llm-as-judge
-    - provider_type: inline::braintrust
-    tool_runtime:
-    - provider_type: remote::brave-search
-    - provider_type: remote::tavily-search
-    - provider_type: inline::rag-runtime
-    - provider_type: remote::model-context-protocol
-    batches:
-    - provider_type: inline::reference
-image_type: venv
-additional_pip_packages:
-- aiosqlite
-- asyncpg
-- sqlalchemy[asyncio]

llama_stack/distributions/starter/run.yaml

@@ -1,281 +0,0 @@
-version: 2
-image_name: starter
-apis:
-- agents
-- batches
-- datasetio
-- eval
-- files
-- inference
-- post_training
-- safety
-- scoring
-- tool_runtime
-- vector_io
-providers:
-  inference:
-  - provider_id: ${env.CEREBRAS_API_KEY:+cerebras}
-    provider_type: remote::cerebras
-    config:
-      base_url: https://api.cerebras.ai
-      api_key: ${env.CEREBRAS_API_KEY:=}
-  - provider_id: ${env.OLLAMA_URL:+ollama}
-    provider_type: remote::ollama
-    config:
-      url: ${env.OLLAMA_URL:=http://localhost:11434}
-  - provider_id: ${env.VLLM_URL:+vllm}
-    provider_type: remote::vllm
-    config:
-      url: ${env.VLLM_URL:=}
-      max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
-      api_token: ${env.VLLM_API_TOKEN:=fake}
-      tls_verify: ${env.VLLM_TLS_VERIFY:=true}
-  - provider_id: ${env.TGI_URL:+tgi}
-    provider_type: remote::tgi
-    config:
-      url: ${env.TGI_URL:=}
-  - provider_id: fireworks
-    provider_type: remote::fireworks
-    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: bedrock
-    provider_type: remote::bedrock
-  - provider_id: ${env.NVIDIA_API_KEY:+nvidia}
-    provider_type: remote::nvidia
-    config:
-      url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
-      api_key: ${env.NVIDIA_API_KEY:=}
-      append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
-  - provider_id: openai
-    provider_type: remote::openai
-    config:
-      api_key: ${env.OPENAI_API_KEY:=}
-      base_url: ${env.OPENAI_BASE_URL:=https://api.openai.com/v1}
-  - provider_id: anthropic
-    provider_type: remote::anthropic
-    config:
-      api_key: ${env.ANTHROPIC_API_KEY:=}
-  - provider_id: gemini
-    provider_type: remote::gemini
-    config:
-      api_key: ${env.GEMINI_API_KEY:=}
-  - provider_id: ${env.VERTEX_AI_PROJECT:+vertexai}
-    provider_type: remote::vertexai
-    config:
-      project: ${env.VERTEX_AI_PROJECT:=}
-      location: ${env.VERTEX_AI_LOCATION:=us-central1}
-  - provider_id: groq
-    provider_type: remote::groq
-    config:
-      url: https://api.groq.com
-      api_key: ${env.GROQ_API_KEY:=}
-  - provider_id: sambanova
-    provider_type: remote::sambanova
-    config:
-      url: https://api.sambanova.ai/v1
-      api_key: ${env.SAMBANOVA_API_KEY:=}
-  - provider_id: ${env.AZURE_API_KEY:+azure}
-    provider_type: remote::azure
-    config:
-      api_key: ${env.AZURE_API_KEY:=}
-      api_base: ${env.AZURE_API_BASE:=}
-      api_version: ${env.AZURE_API_VERSION:=}
-      api_type: ${env.AZURE_API_TYPE:=}
-  - provider_id: sentence-transformers
-    provider_type: inline::sentence-transformers
-  vector_io:
-  - provider_id: faiss
-    provider_type: inline::faiss
-    config:
-      persistence:
-        namespace: vector_io::faiss
-        backend: kv_default
-  - provider_id: sqlite-vec
-    provider_type: inline::sqlite-vec
-    config:
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/sqlite_vec.db
-      persistence:
-        namespace: vector_io::sqlite_vec
-        backend: kv_default
-  - provider_id: ${env.MILVUS_URL:+milvus}
-    provider_type: inline::milvus
-    config:
-      db_path: ${env.MILVUS_DB_PATH:=~/.llama/distributions/starter}/milvus.db
-      persistence:
-        namespace: vector_io::milvus
-        backend: kv_default
-  - provider_id: ${env.CHROMADB_URL:+chromadb}
-    provider_type: remote::chromadb
-    config:
-      url: ${env.CHROMADB_URL:=}
-      persistence:
-        namespace: vector_io::chroma_remote
-        backend: kv_default
-  - provider_id: ${env.PGVECTOR_DB:+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:=}
-      persistence:
-        namespace: vector_io::pgvector
-        backend: kv_default
-  - provider_id: ${env.QDRANT_URL:+qdrant}
-    provider_type: remote::qdrant
-    config:
-      api_key: ${env.QDRANT_API_KEY:=}
-      persistence:
-        namespace: vector_io::qdrant_remote
-        backend: kv_default
-  - provider_id: ${env.WEAVIATE_CLUSTER_URL:+weaviate}
-    provider_type: remote::weaviate
-    config:
-      weaviate_api_key: null
-      weaviate_cluster_url: ${env.WEAVIATE_CLUSTER_URL:=localhost:8080}
-      persistence:
-        namespace: vector_io::weaviate
-        backend: kv_default
-  files:
-  - provider_id: meta-reference-files
-    provider_type: inline::localfs
-    config:
-      storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter/files}
-      metadata_store:
-        table_name: files_metadata
-        backend: sql_default
-  safety:
-  - provider_id: llama-guard
-    provider_type: inline::llama-guard
-    config:
-      excluded_categories: []
-  - provider_id: code-scanner
-    provider_type: inline::code-scanner
-  agents:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      persistence:
-        agent_state:
-          namespace: agents
-          backend: kv_default
-        responses:
-          table_name: responses
-          backend: sql_default
-          max_write_queue_size: 10000
-          num_writers: 4
-  post_training:
-  - provider_id: torchtune-cpu
-    provider_type: inline::torchtune-cpu
-    config:
-      checkpoint_format: meta
-  eval:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      kvstore:
-        namespace: eval
-        backend: kv_default
-  datasetio:
-  - provider_id: huggingface
-    provider_type: remote::huggingface
-    config:
-      kvstore:
-        namespace: datasetio::huggingface
-        backend: kv_default
-  - provider_id: localfs
-    provider_type: inline::localfs
-    config:
-      kvstore:
-        namespace: datasetio::localfs
-        backend: kv_default
-  scoring:
-  - provider_id: basic
-    provider_type: inline::basic
-  - provider_id: llm-as-judge
-    provider_type: inline::llm-as-judge
-  - 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
-  - provider_id: model-context-protocol
-    provider_type: remote::model-context-protocol
-  batches:
-  - provider_id: reference
-    provider_type: inline::reference
-    config:
-      kvstore:
-        namespace: batches
-        backend: kv_default
-storage:
-  backends:
-    kv_default:
-      type: kv_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/kvstore.db
-    sql_default:
-      type: sql_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/sql_store.db
-  stores:
-    metadata:
-      namespace: registry
-      backend: kv_default
-    inference:
-      table_name: inference_store
-      backend: sql_default
-      max_write_queue_size: 10000
-      num_writers: 4
-    conversations:
-      table_name: openai_conversations
-      backend: sql_default
-    prompts:
-      namespace: prompts
-      backend: kv_default
-registered_resources:
-  models: []
-  shields:
-  - shield_id: llama-guard
-    provider_id: ${env.SAFETY_MODEL:+llama-guard}
-    provider_shield_id: ${env.SAFETY_MODEL:=}
-  - shield_id: code-scanner
-    provider_id: ${env.CODE_SCANNER_MODEL:+code-scanner}
-    provider_shield_id: ${env.CODE_SCANNER_MODEL:=}
-  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
-telemetry:
-  enabled: true
-vector_stores:
-  default_provider_id: faiss
-  default_embedding_model:
-    provider_id: sentence-transformers
-    model_id: nomic-ai/nomic-embed-text-v1.5
-safety:
-  default_shield_id: llama-guard

llama_stack/distributions/watsonx/build.yaml

@@ -1,33 +0,0 @@
-version: 2
-distribution_spec:
-  description: Use watsonx for running LLM inference
-  providers:
-    inference:
-    - provider_type: remote::watsonx
-    - provider_type: inline::sentence-transformers
-    vector_io:
-    - provider_type: inline::faiss
-    safety:
-    - provider_type: inline::llama-guard
-    agents:
-    - provider_type: inline::meta-reference
-    eval:
-    - provider_type: inline::meta-reference
-    datasetio:
-    - provider_type: remote::huggingface
-    - provider_type: inline::localfs
-    scoring:
-    - provider_type: inline::basic
-    - provider_type: inline::llm-as-judge
-    - provider_type: inline::braintrust
-    tool_runtime:
-    - provider_type: remote::brave-search
-    - provider_type: remote::tavily-search
-    - provider_type: inline::rag-runtime
-    - provider_type: remote::model-context-protocol
-    files:
-    - provider_type: inline::localfs
-image_type: venv
-additional_pip_packages:
-- aiosqlite
-- sqlalchemy[asyncio]

llama_stack/distributions/watsonx/run.yaml

@@ -1,136 +0,0 @@
-version: 2
-image_name: watsonx
-apis:
-- agents
-- datasetio
-- eval
-- files
-- inference
-- safety
-- scoring
-- tool_runtime
-- vector_io
-providers:
-  inference:
-  - provider_id: watsonx
-    provider_type: remote::watsonx
-    config:
-      url: ${env.WATSONX_BASE_URL:=https://us-south.ml.cloud.ibm.com}
-      api_key: ${env.WATSONX_API_KEY:=}
-      project_id: ${env.WATSONX_PROJECT_ID:=}
-  vector_io:
-  - provider_id: faiss
-    provider_type: inline::faiss
-    config:
-      persistence:
-        namespace: vector_io::faiss
-        backend: kv_default
-  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:
-        agent_state:
-          namespace: agents
-          backend: kv_default
-        responses:
-          table_name: responses
-          backend: sql_default
-          max_write_queue_size: 10000
-          num_writers: 4
-  eval:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      kvstore:
-        namespace: eval
-        backend: kv_default
-  datasetio:
-  - provider_id: huggingface
-    provider_type: remote::huggingface
-    config:
-      kvstore:
-        namespace: datasetio::huggingface
-        backend: kv_default
-  - provider_id: localfs
-    provider_type: inline::localfs
-    config:
-      kvstore:
-        namespace: datasetio::localfs
-        backend: kv_default
-  scoring:
-  - provider_id: basic
-    provider_type: inline::basic
-  - provider_id: llm-as-judge
-    provider_type: inline::llm-as-judge
-  - 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
-  - provider_id: model-context-protocol
-    provider_type: remote::model-context-protocol
-  files:
-  - provider_id: meta-reference-files
-    provider_type: inline::localfs
-    config:
-      storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/watsonx/files}
-      metadata_store:
-        table_name: files_metadata
-        backend: sql_default
-storage:
-  backends:
-    kv_default:
-      type: kv_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/kvstore.db
-    sql_default:
-      type: sql_sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/sql_store.db
-  stores:
-    metadata:
-      namespace: registry
-      backend: kv_default
-    inference:
-      table_name: inference_store
-      backend: sql_default
-      max_write_queue_size: 10000
-      num_writers: 4
-    conversations:
-      table_name: openai_conversations
-      backend: sql_default
-    prompts:
-      namespace: prompts
-      backend: kv_default
-registered_resources:
-  models: []
-  shields: []
-  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
-telemetry:
-  enabled: true

scripts/distro_codegen.py

@@ -55,7 +55,7 @@ def process_distro(distro_dir: Path, progress, change_tracker: ChangedPathTracke
         if template_func := getattr(module, "get_distribution_template", None):
             distro = template_func()
 
-            yaml_output_dir = REPO_ROOT / "llama_stack" / "distributions" / distro.name
+            yaml_output_dir = REPO_ROOT / "src" / "llama_stack" / "distributions" / distro.name
             doc_output_dir = REPO_ROOT / "docs/docs/distributions" / f"{distro.distro_type}_distro"
             change_tracker.add_paths(yaml_output_dir, doc_output_dir)
             distro.save_distribution(

src/llama_stack/distributions/dell/run-with-safety.yaml

@@ -109,6 +109,9 @@ storage:
     conversations:
       table_name: openai_conversations
       backend: sql_default
+    prompts:
+      namespace: prompts
+      backend: kv_default
 registered_resources:
   models:
   - metadata: {}

src/llama_stack/distributions/meta-reference-gpu/run-with-safety.yaml

@@ -122,6 +122,9 @@ storage:
     conversations:
       table_name: openai_conversations
       backend: sql_default
+    prompts:
+      namespace: prompts
+      backend: kv_default
 registered_resources:
   models:
   - metadata: {}

src/llama_stack/distributions/nvidia/run-with-safety.yaml

@@ -111,6 +111,9 @@ storage:
     conversations:
       table_name: openai_conversations
       backend: sql_default
+    prompts:
+      namespace: prompts
+      backend: kv_default
 registered_resources:
   models:
   - metadata: {}