fix(vertex_ai_llama3.py): Fix llama3 streaming issue

Closes https://github.com/BerriAI/litellm/issues/4885

litellm/llms/vertex_ai_llama.py

@@ -103,7 +103,8 @@ class VertexAILlama3Config:
         for param, value in non_default_params.items():
             if param == "max_tokens":
                 optional_params["max_tokens"] = value
-
+            if param == "stream":
+                optional_params["stream"] = value
         return optional_params
 
 

litellm/tests/test_amazing_vertex_completion.py

@@ -937,8 +937,6 @@ async def test_llama_3_httpx(model, sync_mode):
         response_format_tests(response=response)
 
         print(f"response: {response}")
-
-        assert False
     except litellm.RateLimitError as e:
         pass
     except Exception as e: