Add Llama 3.1 8B model to LiteLLM configuration

ai/litellm-config.yaml

@@ -42,6 +42,18 @@ model_list:
       supports_system_messages: false  # vLLM handles system messages differently
       stream: true  # Enable streaming by default
 
+  - model_name: llama-3.1-8b
+    litellm_params:
+      model: hosted_vllm/openai/llama-3.1-8b  # hosted_vllm/openai/ for vLLM via orchestrator
+      api_base: http://100.121.199.88:9000/v1  # RunPod GPU via Tailscale
+      api_key: dummy
+      rpm: 1000
+      tpm: 100000
+      timeout: 600  # 10 minutes for generation
+      stream_timeout: 600
+      supports_system_messages: true  # Llama supports system messages
+      stream: true  # Enable streaming by default
+
 litellm_settings:
   drop_params: false  # DISABLED: Was breaking streaming
   set_verbose: true  # Enable verbose logging for debugging streaming issues