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