Update provider_type -> inline::llama-guard in templates, update run.yaml

distributions/dell-tgi/run.yaml

@@ -19,15 +19,14 @@ providers:
       url: http://127.0.0.1:80
   safety:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::llama-guard
     config:
-      llama_guard_shield:
-        model: Llama-Guard-3-1B
-        excluded_categories: []
-        disable_input_check: false
-        disable_output_check: false
-      prompt_guard_shield:
-        model: Prompt-Guard-86M
+      model: Llama-Guard-3-1B
+      excluded_categories: []
+  - provider_id: meta1
+    provider_type: inline::prompt-guard
+    config:
+      model: Prompt-Guard-86M
   memory:
   - provider_id: meta0
     provider_type: meta-reference

distributions/fireworks/run.yaml

@@ -19,16 +19,16 @@ providers:
       url: https://api.fireworks.ai/inference
       # api_key: <ENTER_YOUR_API_KEY>
   safety:
+  safety:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::llama-guard
     config:
-      llama_guard_shield:
-        model: Llama-Guard-3-1B
-        excluded_categories: []
-        disable_input_check: false
-        disable_output_check: false
-      prompt_guard_shield:
-        model: Prompt-Guard-86M
+      model: Llama-Guard-3-1B
+      excluded_categories: []
+  - provider_id: meta1
+    provider_type: inline::prompt-guard
+    config:
+      model: Prompt-Guard-86M
   memory:
   - provider_id: meta0
     provider_type: meta-reference

distributions/inline-vllm/run.yaml

@@ -21,7 +21,7 @@ providers:
       gpu_memory_utilization: 0.4
       enforce_eager: true
       max_tokens: 4096
-  - provider_id: vllm-safety
+  - provider_id: vllm-inference-safety
     provider_type: inline::vllm
     config:
       model: Llama-Guard-3-1B
@@ -31,14 +31,15 @@ providers:
       max_tokens: 4096
   safety:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::llama-guard
     config:
-      llama_guard_shield:
-        model: Llama-Guard-3-1B
-        excluded_categories: []
-# Uncomment to use prompt guard
-#      prompt_guard_shield:
-#        model: Prompt-Guard-86M
+      model: Llama-Guard-3-1B
+      excluded_categories: []
+  # Uncomment to use prompt guard
+  # - provider_id: meta1
+  #   provider_type: inline::prompt-guard
+  #   config:
+  #     model: Prompt-Guard-86M
   memory:
   - provider_id: meta0
     provider_type: meta-reference

distributions/meta-reference-gpu/run.yaml

@@ -13,7 +13,7 @@ apis:
 - safety
 providers:
   inference:
-  - provider_id: meta-reference-inference
+  - provider_id: inference0
     provider_type: meta-reference
     config:
       model: Llama3.2-3B-Instruct
@@ -21,7 +21,7 @@ providers:
       torch_seed: null
       max_seq_len: 4096
       max_batch_size: 1
-  - provider_id: meta-reference-safety
+  - provider_id: inference1
     provider_type: meta-reference
     config:
       model: Llama-Guard-3-1B
@@ -31,11 +31,14 @@ providers:
       max_batch_size: 1
   safety:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::llama-guard
     config:
-      llama_guard_shield:
-        model: Llama-Guard-3-1B
-        excluded_categories: []
+      model: Llama-Guard-3-1B
+      excluded_categories: []
+  - provider_id: meta1
+    provider_type: inline::prompt-guard
+    config:
+      model: Prompt-Guard-86M
 # Uncomment to use prompt guard
 #      prompt_guard_shield:
 #        model: Prompt-Guard-86M

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

@@ -22,17 +22,25 @@ providers:
       torch_seed: null
       max_seq_len: 2048
       max_batch_size: 1
+  - provider_id: meta1
+    provider_type: meta-reference-quantized
+    config:
+      # not a quantized model !
+      model: Llama-Guard-3-1B
+      quantization: null
+      torch_seed: null
+      max_seq_len: 2048
+      max_batch_size: 1
   safety:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::llama-guard
     config:
-      llama_guard_shield:
-        model: Llama-Guard-3-1B
-        excluded_categories: []
-        disable_input_check: false
-        disable_output_check: false
-      prompt_guard_shield:
-        model: Prompt-Guard-86M
+      model: Llama-Guard-3-1B
+      excluded_categories: []
+  - provider_id: meta1
+    provider_type: inline::prompt-guard
+    config:
+      model: Prompt-Guard-86M
   memory:
   - provider_id: meta0
     provider_type: meta-reference

distributions/ollama-gpu/run.yaml

@@ -19,15 +19,14 @@ providers:
       url: http://127.0.0.1:14343
   safety:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::llama-guard
     config:
-      llama_guard_shield:
-        model: Llama-Guard-3-1B
-        excluded_categories: []
-        disable_input_check: false
-        disable_output_check: false
-      prompt_guard_shield:
-        model: Prompt-Guard-86M
+      model: Llama-Guard-3-1B
+      excluded_categories: []
+  - provider_id: meta1
+    provider_type: inline::prompt-guard
+    config:
+      model: Prompt-Guard-86M
   memory:
   - provider_id: meta0
     provider_type: meta-reference

distributions/ollama/run.yaml

@@ -19,15 +19,14 @@ providers:
       url: http://127.0.0.1:14343
   safety:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::llama-guard
     config:
-      llama_guard_shield:
-        model: Llama-Guard-3-1B
-        excluded_categories: []
-        disable_input_check: false
-        disable_output_check: false
-      prompt_guard_shield:
-        model: Prompt-Guard-86M
+      model: Llama-Guard-3-1B
+      excluded_categories: []
+  - provider_id: meta1
+    provider_type: inline::prompt-guard
+    config:
+      model: Prompt-Guard-86M
   memory:
   - provider_id: meta0
     provider_type: meta-reference

distributions/remote-vllm/run.yaml

@@ -19,15 +19,14 @@ providers:
       url: http://127.0.0.1:8000
   safety:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::llama-guard
     config:
-      llama_guard_shield:
-        model: Llama-Guard-3-1B
-        excluded_categories: []
-        disable_input_check: false
-        disable_output_check: false
-      prompt_guard_shield:
-        model: Prompt-Guard-86M
+      model: Llama-Guard-3-1B
+      excluded_categories: []
+  - provider_id: meta1
+    provider_type: inline::prompt-guard
+    config:
+      model: Prompt-Guard-86M
   memory:
   - provider_id: meta0
     provider_type: meta-reference

distributions/tgi/run.yaml

@@ -19,15 +19,14 @@ providers:
       url: http://127.0.0.1:5009
   safety:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::llama-guard
     config:
-      llama_guard_shield:
-        model: Llama-Guard-3-1B
-        excluded_categories: []
-        disable_input_check: false
-        disable_output_check: false
-      prompt_guard_shield:
-        model: Prompt-Guard-86M
+      model: Llama-Guard-3-1B
+      excluded_categories: []
+  - provider_id: meta1
+    provider_type: inline::prompt-guard
+    config:
+      model: Prompt-Guard-86M
   memory:
   - provider_id: meta0
     provider_type: meta-reference

distributions/together/run.yaml

@@ -20,15 +20,14 @@ providers:
       # api_key: <ENTER_YOUR_API_KEY>
   safety:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::llama-guard
     config:
-      llama_guard_shield:
-        model: Llama-Guard-3-1B
-        excluded_categories: []
-        disable_input_check: false
-        disable_output_check: false
-      prompt_guard_shield:
-        model: Prompt-Guard-86M
+      model: Llama-Guard-3-1B
+      excluded_categories: []
+  - provider_id: meta1
+    provider_type: inline::prompt-guard
+    config:
+      model: Prompt-Guard-86M
   memory:
   - provider_id: meta0
     provider_type: remote::weaviate

docs/source/distribution_dev/building_distro.md

@@ -36,9 +36,9 @@ the provider types (implementations) you want to use for these APIs.
 Tip: use <TAB> to see options for the providers.
 
 > Enter provider for API inference: meta-reference
-> Enter provider for API safety: meta-reference
+> Enter provider for API safety: inline::llama-guard
 > Enter provider for API agents: meta-reference
-> Enter provider for API memory: meta-reference
+> Enter provider for API memory: inline::faiss
 > Enter provider for API datasetio: meta-reference
 > Enter provider for API scoring: meta-reference
 > Enter provider for API eval: meta-reference
@@ -203,8 +203,8 @@ distribution_spec:
   description: Like local, but use ollama for running LLM inference
   providers:
     inference: remote::ollama
-    memory: meta-reference
-    safety: meta-reference
+    memory: inline::faiss
+    safety: inline::llama-guard
     agents: meta-reference
     telemetry: meta-reference
 image_type: conda

llama_stack/providers/tests/safety/fixtures.py

@@ -11,6 +11,7 @@ from llama_stack.apis.shields import ShieldType
 
 from llama_stack.distribution.datatypes import Api, Provider
 from llama_stack.providers.inline.safety.llama_guard import LlamaGuardConfig
+from llama_stack.providers.inline.safety.prompt_guard import PromptGuardConfig
 from llama_stack.providers.remote.safety.bedrock import BedrockSafetyConfig
 
 from llama_stack.providers.tests.resolver import resolve_impls_for_test_v2
@@ -44,6 +45,22 @@ def safety_llama_guard(safety_model) -> ProviderFixture:
     )
 
 
+# TODO: this is not tested yet; we would need to configure the run_shield() test
+# and parametrize it with the "prompt" for testing depending on the safety fixture
+# we are using.
+@pytest.fixture(scope="session")
+def safety_prompt_guard() -> ProviderFixture:
+    return ProviderFixture(
+        providers=[
+            Provider(
+                provider_id="inline::prompt-guard",
+                provider_type="inline::prompt-guard",
+                config=PromptGuardConfig().model_dump(),
+            )
+        ],
+    )
+
+
 @pytest.fixture(scope="session")
 def safety_bedrock() -> ProviderFixture:
     return ProviderFixture(

llama_stack/templates/bedrock/build.yaml

@@ -3,7 +3,7 @@ distribution_spec:
   description: Use Amazon Bedrock APIs.
   providers:
     inference: remote::bedrock
-    memory: meta-reference
-    safety: meta-reference
+    memory: inline::faiss
+    safety: inline::llama-guard
     agents: meta-reference
     telemetry: meta-reference

llama_stack/templates/databricks/build.yaml

@@ -3,7 +3,7 @@ distribution_spec:
   description: Use Databricks for running LLM inference
   providers:
     inference: remote::databricks
-    memory: meta-reference
-    safety: meta-reference
+    memory: inline::faiss
+    safety: inline::llama-guard
     agents: meta-reference
     telemetry: meta-reference

llama_stack/templates/fireworks/build.yaml

@@ -6,6 +6,6 @@ distribution_spec:
     memory:
     - meta-reference
     - remote::weaviate
-    safety: meta-reference
+    safety: inline::llama-guard
     agents: meta-reference
     telemetry: meta-reference

llama_stack/templates/hf-endpoint/build.yaml

@@ -3,7 +3,7 @@ distribution_spec:
   description: "Like local, but use Hugging Face Inference Endpoints for running LLM inference.\nSee https://hf.co/docs/api-endpoints."
   providers:
     inference: remote::hf::endpoint
-    memory: meta-reference
-    safety: meta-reference
+    memory: inline::faiss
+    safety: inline::llama-guard
     agents: meta-reference
     telemetry: meta-reference

llama_stack/templates/hf-serverless/build.yaml

@@ -3,7 +3,7 @@ distribution_spec:
   description: "Like local, but use Hugging Face Inference API (serverless) for running LLM inference.\nSee https://hf.co/docs/api-inference."
   providers:
     inference: remote::hf::serverless
-    memory: meta-reference
-    safety: meta-reference
+    memory: inline::faiss
+    safety: inline::llama-guard
     agents: meta-reference
     telemetry: meta-reference

llama_stack/templates/inline-vllm/build.yaml

@@ -8,6 +8,6 @@ distribution_spec:
     - meta-reference
     - remote::chromadb
     - remote::pgvector
-    safety: meta-reference
+    safety: inline::llama-guard
     agents: meta-reference
     telemetry: meta-reference

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

@@ -8,6 +8,6 @@ distribution_spec:
     - meta-reference
     - remote::chromadb
     - remote::pgvector
-    safety: meta-reference
+    safety: inline::llama-guard
     agents: meta-reference
     telemetry: meta-reference

llama_stack/templates/meta-reference-quantized-gpu/build.yaml

@@ -8,6 +8,6 @@ distribution_spec:
     - meta-reference
     - remote::chromadb
     - remote::pgvector
-    safety: meta-reference
+    safety: inline::llama-guard
     agents: meta-reference
     telemetry: meta-reference

llama_stack/templates/ollama/build.yaml

@@ -7,6 +7,6 @@ distribution_spec:
     - meta-reference
     - remote::chromadb
     - remote::pgvector
-    safety: meta-reference
+    safety: inline::llama-guard
     agents: meta-reference
     telemetry: meta-reference

llama_stack/templates/remote-vllm/build.yaml

@@ -7,6 +7,6 @@ distribution_spec:
     - meta-reference
     - remote::chromadb
     - remote::pgvector
-    safety: meta-reference
+    safety: inline::llama-guard
     agents: meta-reference
     telemetry: meta-reference

llama_stack/templates/tgi/build.yaml

@@ -7,6 +7,6 @@ distribution_spec:
     - meta-reference
     - remote::chromadb
     - remote::pgvector
-    safety: meta-reference
+    safety: inline::llama-guard
     agents: meta-reference
     telemetry: meta-reference

llama_stack/templates/together/build.yaml

@@ -6,6 +6,6 @@ distribution_spec:
     memory:
     - meta-reference
     - remote::weaviate
-    safety: meta-reference
+    safety: inline::llama-guard
     agents: meta-reference
     telemetry: meta-reference