perf: defer fastapi and tiktoken BPE imports out of import litellm

This defers FastAPI, Starlette, and the cl100k BPE table until the paths that use them run

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

litellm/integrations/custom_guardrail.py

@@ -35,11 +35,6 @@ from litellm.types.utils import (
     StandardLoggingGuardrailInformation,
 )
 
-try:
-    from fastapi.exceptions import HTTPException
-except ImportError:
-    HTTPException = None
-
 if TYPE_CHECKING:
     from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
     from litellm.llms.base_llm.guardrail_translation.base_translation import BaseTranslation
@@ -107,9 +102,11 @@ def is_guardrail_intervention(e: Exception) -> bool:
         ),
     ):
         return True
-    if HTTPException is not None and isinstance(e, HTTPException) and e.status_code in _GUARDRAIL_BLOCK_STATUS_CODES:
-        return True
-    return False
+    try:
+        from fastapi.exceptions import HTTPException
+    except ImportError:
+        return False
+    return isinstance(e, HTTPException) and e.status_code in _GUARDRAIL_BLOCK_STATUS_CODES
 
 
 def _strict_guardrail_modes_enabled() -> bool:

litellm/integrations/gcs_bucket/gcs_bucket.py

@@ -14,7 +14,6 @@ from litellm.integrations.gcs_bucket.gcs_bucket_base import GCSBucketBase
 from litellm.litellm_core_utils.cloud_storage_security import (
     sanitize_cloud_object_component,
 )
-from litellm.proxy._types import CommonProxyErrors
 from litellm.types.integrations.base_health_check import IntegrationHealthCheckStatus
 from litellm.types.integrations.gcs_bucket import *
 from litellm.types.utils import StandardLoggingPayload
@@ -27,6 +26,7 @@ else:
 
 class GCSBucketLogger(GCSBucketBase, AdditionalLoggingUtils):
     def __init__(self, bucket_name: str | None = None) -> None:
+        from litellm.proxy._types import CommonProxyErrors
         from litellm.proxy.proxy_server import premium_user
 
         self.batch_size = int(os.getenv("GCS_BATCH_SIZE", GCS_DEFAULT_BATCH_SIZE))
@@ -52,6 +52,7 @@ class GCSBucketLogger(GCSBucketBase, AdditionalLoggingUtils):
 
     #### ASYNC ####
     async def async_log_success_event(self, kwargs, response_obj, start_time, end_time):
+        from litellm.proxy._types import CommonProxyErrors
         from litellm.proxy.proxy_server import premium_user
 
         if premium_user is not True:

litellm/litellm_core_utils/token_counter.py

@@ -15,6 +15,7 @@ from typing_extensions import ParamSpec, TypeVar
 
 import litellm
 from litellm import verbose_logger
+from litellm._lazy_imports import _get_default_encoding
 from litellm.constants import (
     DEFAULT_IMAGE_HEIGHT,
     DEFAULT_IMAGE_TOKEN_COUNT,
@@ -29,7 +30,6 @@ from litellm.constants import (
     TOKEN_COUNTER_MAX_EXACT_CHARS,
 )
 from litellm.litellm_core_utils.asyncify import asyncify
-from litellm.litellm_core_utils.default_encoding import encoding as default_encoding
 from litellm.litellm_core_utils.url_utils import safe_get
 from litellm.llms.custom_httpx.http_handler import _get_httpx_client
 from litellm.types.llms.anthropic import (
@@ -638,7 +638,7 @@ def _get_exact_count_function(
     else:
 
         def encode_length(text: str) -> int:
-            return len(default_encoding.encode(text, disallowed_special=()))
+            return len(_get_default_encoding().encode(text, disallowed_special=()))
 
         return _get_tiktoken_count_function(encode_length)
 

tests/test_litellm/litellm_core_utils/test_token_counter.py

@@ -98,6 +98,13 @@ def test_token_counter_short_text_matches_tiktoken(text):
     assert token_counter_new(model="us.anthropic.claude-sonnet-4-6", text=text) == expected
 
 
+def test_token_counter_default_encoding_matches_cl100k():
+    encoding: Final = tiktoken.get_encoding("cl100k_base")
+    expected: Final = len(encoding.encode("hello world", disallowed_special=()))
+
+    assert token_counter_new(model="", text="hello world") == expected
+
+
 def test_token_counter_text_over_chunk_boundary_stays_close_to_tiktoken():
     text = ("The quick brown fox jumps over the lazy dog. " * 30)[:1025]
     encoding = tiktoken.get_encoding("cl100k_base")

tests/test_litellm/test_lazy_imports.py

@@ -1,6 +1,9 @@
 """Simple tests for lazy import functionality."""
 
+import os
+import subprocess
 import sys
+from typing import Final
 
 import pytest
 
@@ -38,6 +41,22 @@ from litellm._lazy_imports import (
 )
 
 
+def test_import_litellm_does_not_load_fastapi_or_bpe_table():
+    result: Final = subprocess.run(
+        [
+            sys.executable,
+            "-c",
+            "import sys, litellm; print(','.join(m for m in ('fastapi','starlette','litellm.litellm_core_utils.default_encoding') if m in sys.modules))",
+        ],
+        check=True,
+        capture_output=True,
+        text=True,
+        env={**os.environ, "LITELLM_LOCAL_MODEL_COST_MAP": "True"},
+    )
+
+    assert result.stdout.strip() == ""
+
+
 def _clear_names_from_globals(names: tuple):
     """Clear all names from litellm globals."""
     # Get the actual globals dict, not a copy