fixes: expose flag to disable token counter (#11344)

* fixes: expose flag to disable token counter

* fix add disable_token_counter

litellm/__init__.py

@@ -217,6 +217,7 @@ use_client: bool = False
 ssl_verify: Union[str, bool] = True
 ssl_certificate: Optional[str] = None
 disable_streaming_logging: bool = False
+disable_token_counter: bool = False
 disable_add_transform_inline_image_block: bool = False
 in_memory_llm_clients_cache: LLMClientCache = LLMClientCache()
 safe_memory_mode: bool = False

litellm/litellm_core_utils/token_counter.py

@@ -362,6 +362,15 @@ def token_counter(
     """
     from litellm.utils import convert_list_message_to_dict
 
+    #########################################################
+    # Flag to disable token counter
+    # We've gotten reports of this consuming CPU cycles,
+    # exposing this flag to allow users to disable
+    # it to confirm if this is indeed the issue
+    #########################################################
+    if litellm.disable_token_counter is True:
+        return 0
+
     verbose_logger.debug(
         f"messages in token_counter: {messages}, text in token_counter: {text}"
     )

litellm/proxy/proxy_config.yaml

@@ -4,6 +4,5 @@ model_list:
       model: openai/*
 
 
-
-
-
+litellm_settings:
+  disable_token_counter: True

litellm/utils.py

@@ -1697,6 +1697,16 @@ def token_counter(
 
     Kept for backwards compatibility.
     """
+
+    #########################################################
+    # Flag to disable token counter
+    # We've gotten reports of this consuming CPU cycles,
+    # exposing this flag to allow users to disable
+    # it to confirm if this is indeed the issue
+    #########################################################
+    if litellm.disable_token_counter is True:
+        return 0
+
     return token_counter_new(
         model,
         custom_tokenizer,