feat: consolidate most distros into "starter" (#2516)

# What does this PR do? * Removes a bunch of distros * Removed distros were added into the "starter" distribution * Doc for "starter" has been added * Partially reverts https://github.com/meta-llama/llama-stack/pull/2482 since inference providers are disabled by default and can be turned on manually via env variable. * Disables safety in starter distro Closes: https://github.com/meta-llama/llama-stack/issues/2502. ~Needs: https://github.com/meta-llama/llama-stack/pull/2482 for Ollama to work properly in the CI.~ TODO: - [ ] We can only update `install.sh` when we get a new release. - [x] Update providers documentation - [ ] Update notebooks to reference starter instead of ollama Signed-off-by: Sébastien Han <seb@redhat.com>
2025-07-21 20:18:52 +00:00 · 2025-07-04 15:58:03 +02:00 · 2025-07-04 15:58:03 +02:00 · c4349f532b
commit c4349f532b
parent f77d4d91f5
132 changed files with 1009 additions and 10845 deletions
--- a/llama_stack/templates/nvidia/run.yaml
+++ b/llama_stack/templates/nvidia/run.yaml
@ -1,225 +0,0 @@
-version: 2
-image_name: nvidia
-apis:
- agents
- datasetio
- eval
- inference
- post_training
- safety
- scoring
- telemetry
- 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:
-      kvstore:
-        type: sqlite
-        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/faiss_store.db
-  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_store:
-        type: sqlite
-        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/agents_store.db
-      responses_store:
-        type: sqlite
-        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/responses_store.db
-  telemetry:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      service_name: "${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:
-  - 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
-    config: {}
-  tool_runtime:
-  - provider_id: rag-runtime
-    provider_type: inline::rag-runtime
-    config: {}
-metadata_store:
-  type: sqlite
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/registry.db
-inference_store:
-  type: sqlite
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/inference_store.db
-models:
- metadata: {}
-  model_id: meta/llama3-8b-instruct
-  provider_id: nvidia
-  provider_model_id: meta/llama3-8b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3-8B-Instruct
-  provider_id: nvidia
-  provider_model_id: meta/llama3-8b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta/llama3-70b-instruct
-  provider_id: nvidia
-  provider_model_id: meta/llama3-70b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3-70B-Instruct
-  provider_id: nvidia
-  provider_model_id: meta/llama3-70b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta/llama-3.1-8b-instruct
-  provider_id: nvidia
-  provider_model_id: meta/llama-3.1-8b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.1-8B-Instruct
-  provider_id: nvidia
-  provider_model_id: meta/llama-3.1-8b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta/llama-3.1-70b-instruct
-  provider_id: nvidia
-  provider_model_id: meta/llama-3.1-70b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.1-70B-Instruct
-  provider_id: nvidia
-  provider_model_id: meta/llama-3.1-70b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta/llama-3.1-405b-instruct
-  provider_id: nvidia
-  provider_model_id: meta/llama-3.1-405b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
-  provider_id: nvidia
-  provider_model_id: meta/llama-3.1-405b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta/llama-3.2-1b-instruct
-  provider_id: nvidia
-  provider_model_id: meta/llama-3.2-1b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-1B-Instruct
-  provider_id: nvidia
-  provider_model_id: meta/llama-3.2-1b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta/llama-3.2-3b-instruct
-  provider_id: nvidia
-  provider_model_id: meta/llama-3.2-3b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-3B-Instruct
-  provider_id: nvidia
-  provider_model_id: meta/llama-3.2-3b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta/llama-3.2-11b-vision-instruct
-  provider_id: nvidia
-  provider_model_id: meta/llama-3.2-11b-vision-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
-  provider_id: nvidia
-  provider_model_id: meta/llama-3.2-11b-vision-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta/llama-3.2-90b-vision-instruct
-  provider_id: nvidia
-  provider_model_id: meta/llama-3.2-90b-vision-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
-  provider_id: nvidia
-  provider_model_id: meta/llama-3.2-90b-vision-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta/llama-3.3-70b-instruct
-  provider_id: nvidia
-  provider_model_id: meta/llama-3.3-70b-instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.3-70B-Instruct
-  provider_id: nvidia
-  provider_model_id: meta/llama-3.3-70b-instruct
-  model_type: llm
- metadata:
-    embedding_dimension: 2048
-    context_length: 8192
-  model_id: nvidia/llama-3.2-nv-embedqa-1b-v2
-  provider_id: nvidia
-  provider_model_id: nvidia/llama-3.2-nv-embedqa-1b-v2
-  model_type: embedding
- metadata:
-    embedding_dimension: 1024
-    context_length: 512
-  model_id: nvidia/nv-embedqa-e5-v5
-  provider_id: nvidia
-  provider_model_id: nvidia/nv-embedqa-e5-v5
-  model_type: embedding
- metadata:
-    embedding_dimension: 4096
-    context_length: 512
-  model_id: nvidia/nv-embedqa-mistral-7b-v2
-  provider_id: nvidia
-  provider_model_id: nvidia/nv-embedqa-mistral-7b-v2
-  model_type: embedding
- metadata:
-    embedding_dimension: 1024
-    context_length: 512
-  model_id: snowflake/arctic-embed-l
-  provider_id: nvidia
-  provider_model_id: snowflake/arctic-embed-l
-  model_type: embedding
-shields: []
-vector_dbs: []
-datasets: []
-scoring_fns: []
-benchmarks: []
-tool_groups:
- toolgroup_id: builtin::rag
-  provider_id: rag-runtime
-server:
-  port: 8321