fix: remove vllm embedding

ai/litellm-config.yaml

@@ -42,15 +42,6 @@ model_list:
       supports_system_messages: true # Llama supports system messages
       stream: true # Enable streaming by default
 
-  # Embeddings - BGE Large (Port 8002)
-  - model_name: bge-large-en-v1.5
-    litellm_params:
-      model: hosted_vllm/BAAI/bge-large-en-v1.5
-      api_base: os.environ/GPU_VLLM_EMBED_URL # Direct to vLLM embedding server
-      api_key: "EMPTY"
-      rpm: 1000
-      tpm: 500000
-
 litellm_settings:
   drop_params: false # DISABLED: Was breaking streaming
   set_verbose: true # Enable verbose logging for debugging streaming issues