diff --git a/litellm/llms/ollama.py b/litellm/llms/ollama.py
index f2a9b0df4d1..e2be1c2d5de 100644
--- a/litellm/llms/ollama.py
+++ b/litellm/llms/ollama.py
@@ -195,7 +195,7 @@ async def ollama_acompletion(url, data, model_response, encoding, logging_obj):
                 raise OllamaError(status_code=resp.status, message=text)
             
             completion_string = ""
-            async for line in resp.content.iter_any():
+            async for line in resp.content:
                 if line:
                     try:
                         json_chunk = line.decode("utf-8")
diff --git a/litellm/main.py b/litellm/main.py
index 52d2ae5b663..1e2a8323a4c 100644
--- a/litellm/main.py
+++ b/litellm/main.py
@@ -2026,11 +2026,9 @@ async def atext_completion(*args, **kwargs):
                 response = text_completion(*args, **kwargs)
             else:
                 # Await normally
-                init_response = await loop.run_in_executor(None, func_with_context)
-                if isinstance(init_response, dict) or isinstance(init_response, ModelResponse): ## CACHING SCENARIO 
-                    response = init_response
-                elif asyncio.iscoroutine(init_response):
-                    response = await init_response
+                response = await loop.run_in_executor(None, func_with_context)
+                if asyncio.iscoroutine(response):
+                    response = await response
         else: 
             # Call the synchronous function using run_in_executor
             response =  await loop.run_in_executor(None, func_with_context)