example inference router run config

llama_stack/apis/inference/client.py

@@ -101,16 +101,17 @@ async def run_main(host: str, port: int, stream: bool):
     async for log in EventLogger().log(iterator):
         log.print()
 
-    cprint(f"User>{message.content}", "green")
-    iterator = client.chat_completion(
-        ChatCompletionRequest(
-            model="Meta-Llama3.1-8B",
-            messages=[message],
-            stream=stream,
-        )
-    )
-    async for log in EventLogger().log(iterator):
-        log.print()
+    # For testing models routing
+    # cprint(f"User>{message.content}", "green")
+    # iterator = client.chat_completion(
+    #     ChatCompletionRequest(
+    #         model="Meta-Llama3.1-8B",
+    #         messages=[message],
+    #         stream=stream,
+    #     )
+    # )
+    # async for log in EventLogger().log(iterator):
+    #     log.print()
 
 
 def main(host: str, port: int, stream: bool = True):

llama_stack/configs/examples/local-router-run.yaml

@@ -0,0 +1,64 @@
+built_at: '2024-09-18T13:41:17.656743'
+image_name: local
+docker_image: null
+conda_env: local
+apis_to_serve:
+- inference
+- memory
+- safety
+- telemetry
+- agents
+- models
+provider_map:
+  inference: models-router
+  safety:
+    provider_id: meta-reference
+    config:
+      llama_guard_shield:
+        model: Llama-Guard-3-8B
+        excluded_categories: []
+        disable_input_check: false
+        disable_output_check: false
+      prompt_guard_shield:
+        model: Prompt-Guard-86M
+  telemetry:
+    provider_id: meta-reference
+    config: {}
+  agents:
+    provider_id: meta-reference
+    config: {}
+  models:
+    provider_id: builtin
+    config:
+      models_config:
+      - core_model_id: Meta-Llama3.1-8B-Instruct
+        provider_id: meta-reference
+        api: inference
+        config:
+          model: Meta-Llama3.1-8B-Instruct
+          quantization: null
+          torch_seed: null
+          max_seq_len: 4096
+          max_batch_size: 1
+      - core_model_id: Meta-Llama3.1-8B
+        provider_id: meta-reference
+        api: inference
+        config:
+          model: Meta-Llama3.1-8B
+          quantization: null
+          torch_seed: null
+          max_seq_len: 4096
+          max_batch_size: 1
+      - core_model_id: Llama-Guard-3-8B
+        provider_id: meta-reference
+        api: safety
+        config:
+          model: Llama-Guard-3-8B
+          excluded_categories: []
+          disable_input_check: false
+          disable_output_check: false
+      - core_model_id: Prompt-Guard-86M
+        provider_id: meta-reference
+        api: safety
+        config:
+          model: Prompt-Guard-86M