diff --git a/litellm/integrations/langfuse.py b/litellm/integrations/langfuse.py
index e6f48a5bd..8ef692b21 100644
--- a/litellm/integrations/langfuse.py
+++ b/litellm/integrations/langfuse.py
@@ -14,7 +14,7 @@ class LangFuseLogger:
         try:
             from langfuse import Langfuse
         except Exception as e:
-            raise Exception("\033[91mLangfuse not installed, try running 'pip install langfuse' to fix this error\033[0m", e)
+            raise Exception(f"\033[91mLangfuse not installed, try running 'pip install langfuse' to fix this error: {e}\033[0m")
         # Instance variables
         self.secret_key = os.getenv("LANGFUSE_SECRET_KEY")
         self.public_key = os.getenv("LANGFUSE_PUBLIC_KEY")
diff --git a/litellm/tests/test_langfuse.py b/litellm/tests/test_langfuse.py
index 60aaf006d..edab20a38 100644
--- a/litellm/tests/test_langfuse.py
+++ b/litellm/tests/test_langfuse.py
@@ -1,7 +1,8 @@
 import sys
 import os
-import io
-
+import io, asyncio
+import logging
+logging.basicConfig(level=logging.DEBUG)
 sys.path.insert(0, os.path.abspath('../..'))
 
 from litellm import completion
@@ -11,7 +12,18 @@ litellm.success_callback = ["langfuse"]
 # litellm.set_verbose = True
 import time
 
+def test_langfuse_logging_async(): 
+    async def _test_langfuse():
+        await litellm.acompletion(
+            model="gpt-3.5-turbo",
+            prompt="This is a test",
+            max_tokens=1000,
+            temperature=0.7,
+        )
+    response = asyncio.run(_test_langfuse())
+    print(f"response: {response}")
 
+test_langfuse_logging_async()
 
 def test_langfuse_logging():
     try:
@@ -27,7 +39,7 @@ def test_langfuse_logging():
     except Exception as e:
         print(e)
 
-test_langfuse_logging()
+# test_langfuse_logging()
 
 def test_langfuse_logging_custom_generation_name():
     try:
@@ -47,7 +59,7 @@ def test_langfuse_logging_custom_generation_name():
     except Exception as e:
         print(e)
 
-test_langfuse_logging_custom_generation_name()
+# test_langfuse_logging_custom_generation_name()
 
 def test_langfuse_logging_function_calling():
     function1 = [
@@ -80,7 +92,7 @@ def test_langfuse_logging_function_calling():
     except Exception as e:
         print(e)
 
-test_langfuse_logging_function_calling()
+# test_langfuse_logging_function_calling()
 
 
 
diff --git a/litellm/utils.py b/litellm/utils.py
index c08517ae6..8b2d10207 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -835,8 +835,9 @@ def client(original_function):
             logging_obj = Logging(model=model, messages=messages, stream=stream, litellm_call_id=kwargs["litellm_call_id"], function_id=function_id, call_type=call_type, start_time=start_time)
             return logging_obj
         except Exception as e:  # DO NOT BLOCK running the function because of this
-            print_verbose(f"[Non-Blocking] {traceback.format_exc()}; args - {args}; kwargs - {kwargs}")
-        pass
+            import logging
+            logging.debug(f"[Non-Blocking] {traceback.format_exc()}; args - {args}; kwargs - {kwargs}")
+            raise e
     
     def crash_reporting(*args, **kwargs):
         if litellm.telemetry:
@@ -860,6 +861,7 @@ def client(original_function):
     def wrapper(*args, **kwargs):
         start_time = datetime.datetime.now()
         result = None
+        logging_obj = None
 
         # only set litellm_call_id if its not in kwargs
         if "litellm_call_id" not in kwargs:
@@ -948,17 +950,18 @@ def client(original_function):
             crash_reporting(*args, **kwargs, exception=traceback_exception)
             end_time = datetime.datetime.now()
             # LOG FAILURE - handle streaming failure logging in the _next_ object, remove `handle_failure` once it's deprecated
-            threading.Thread(target=logging_obj.failure_handler, args=(e, traceback_exception, start_time, end_time)).start()
-            my_thread = threading.Thread(
-                target=handle_failure,
-                args=(e, traceback_exception, start_time, end_time, args, kwargs),
-            )  # don't interrupt execution of main thread
-            my_thread.start()
-            if hasattr(e, "message"):
-                if (
-                    liteDebuggerClient and liteDebuggerClient.dashboard_url != None
-                ):  # make it easy to get to the debugger logs if you've initialized it
-                    e.message += f"\n Check the log in your dashboard - {liteDebuggerClient.dashboard_url}"
+            if logging_obj:
+                threading.Thread(target=logging_obj.failure_handler, args=(e, traceback_exception, start_time, end_time)).start()
+                my_thread = threading.Thread(
+                    target=handle_failure,
+                    args=(e, traceback_exception, start_time, end_time, args, kwargs),
+                )  # don't interrupt execution of main thread
+                my_thread.start()
+                if hasattr(e, "message"):
+                    if (
+                        liteDebuggerClient and liteDebuggerClient.dashboard_url != None
+                    ):  # make it easy to get to the debugger logs if you've initialized it
+                        e.message += f"\n Check the log in your dashboard - {liteDebuggerClient.dashboard_url}"
             raise e
     return wrapper