Add Llama 3.1 8B model to orchestrator

model-orchestrator/models.yaml

@@ -13,6 +13,16 @@ models:
     endpoint: /v1/chat/completions
     description: "Qwen 2.5 7B Instruct - Fast text generation, no authentication required"
 
+  llama-3.1-8b:
+    type: text
+    framework: vllm
+    service_script: models/vllm/server.py
+    port: 8001
+    vram_gb: 17
+    startup_time_seconds: 120
+    endpoint: /v1/chat/completions
+    description: "Llama 3.1 8B Instruct - Meta's latest model"
+
 # Example: Add more models easily by uncommenting and customizing below
 
 # Future Text Models: