perf: guard orjson import with fallback, pre-parse httpx URLs, fix docstring

Addresses three review concerns and adds httpx URL caching:

1. safe_json_dumps.py: Guard orjson import with try/except fallback to
   stdlib json. This module is on the core SDK import path via
   _logging.py — unconditional orjson import would break plain
   'pip install litellm' (non-proxy) users.

2. router.py print_deployment: Update docstring to accurately describe
   the reduced return shape (model_name + litellm_params only).

3. run_perf_comparison.sh: Fix locustfile reference to use the correct
   locustfile_perf.py instead of locustfile.py.

4. httpx URL pre-parsing (~7.8us -> ~0.4us per request, 19x speedup):
   Add _parse_url() with LRU cache (maxsize=64) that pre-parses URL
   strings into httpx.URL objects. Applied to all HTTP methods (GET,
   POST, PUT, PATCH, DELETE) in both AsyncHTTPHandler and HTTPHandler.
   Eliminates regex-heavy re.finditer inside httpx._urlparse on every
   request — confirmed as a GIL hotspot in py-spy thread dumps.

Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>

litellm/litellm_core_utils/safe_json_dumps.py

@@ -1,10 +1,17 @@
+import json
 from typing import Any, Union
 
-import orjson
 from pydantic import BaseModel
 
 from litellm.constants import DEFAULT_MAX_RECURSE_DEPTH
 
+try:
+    import orjson
+
+    _has_orjson = True
+except ImportError:
+    _has_orjson = False
+
 
 def safe_dumps(data: Any, max_depth: int = DEFAULT_MAX_RECURSE_DEPTH) -> str:
     """
@@ -52,4 +59,6 @@ def safe_dumps(data: Any, max_depth: int = DEFAULT_MAX_RECURSE_DEPTH) -> str:
                 return "Unserializable Object"
 
     safe_data = _serialize(data, set(), 0)
-    return orjson.dumps(safe_data, default=str).decode()
+    if _has_orjson:
+        return orjson.dumps(safe_data, default=str).decode()
+    return json.dumps(safe_data, default=str)

litellm/llms/custom_httpx/http_handler.py

@@ -1,4 +1,5 @@
 import asyncio
+import functools
 import os
 import ssl
 import sys
@@ -51,6 +52,14 @@ try:
 except Exception:
     version = "0.0.0"
 
+
+@functools.lru_cache(maxsize=64)
+def _parse_url(url: str) -> httpx.URL:
+    """Pre-parse a URL string into an httpx.URL to avoid regex-heavy
+    parsing inside httpx._merge_url on every request (~7μs → ~0.4μs)."""
+    return httpx.URL(url)
+
+
 def get_default_headers() -> dict:
     """
     Get default headers for HTTP requests.
@@ -424,7 +433,7 @@ class AsyncHTTPHandler:
         params.update(HTTPHandler.extract_query_params(url))
 
         response = await self.client.get(
-            url, params=params, headers=headers, follow_redirects=_follow_redirects  # type: ignore
+            _parse_url(url), params=params, headers=headers, follow_redirects=_follow_redirects  # type: ignore
         )
         return response
 
@@ -452,9 +461,10 @@ class AsyncHTTPHandler:
                 data, content
             )
 
+            parsed_url = _parse_url(url)
             req = self.client.build_request(
                 "POST",
-                url,
+                parsed_url,
                 data=request_data,
                 json=json,
                 params=params,
@@ -533,7 +543,7 @@ class AsyncHTTPHandler:
             )
 
             req = self.client.build_request(
-                "PUT", url, data=request_data, json=json, params=params, headers=headers, timeout=timeout, content=request_content  # type: ignore
+                "PUT", _parse_url(url), data=request_data, json=json, params=params, headers=headers, timeout=timeout, content=request_content  # type: ignore
             )
             response = await self.client.send(req)
             response.raise_for_status()
@@ -599,7 +609,7 @@ class AsyncHTTPHandler:
             )
 
             req = self.client.build_request(
-                "PATCH", url, data=request_data, json=json, params=params, headers=headers, timeout=timeout, content=request_content  # type: ignore
+                "PATCH", _parse_url(url), data=request_data, json=json, params=params, headers=headers, timeout=timeout, content=request_content  # type: ignore
             )
             response = await self.client.send(req)
             response.raise_for_status()
@@ -665,7 +675,7 @@ class AsyncHTTPHandler:
             )
 
             req = self.client.build_request(
-                "DELETE", url, data=request_data, json=json, params=params, headers=headers, timeout=timeout, content=request_content  # type: ignore
+                "DELETE", _parse_url(url), data=request_data, json=json, params=params, headers=headers, timeout=timeout, content=request_content  # type: ignore
             )
             response = await self.client.send(req, stream=stream)
             response.raise_for_status()
@@ -717,7 +727,7 @@ class AsyncHTTPHandler:
         request_data, request_content = _prepare_request_data_and_content(data, content)
 
         req = client.build_request(
-            "POST", url, data=request_data, json=json, params=params, headers=headers, content=request_content  # type: ignore
+            "POST", _parse_url(url), data=request_data, json=json, params=params, headers=headers, content=request_content  # type: ignore
         )
         response = await client.send(req, stream=stream)
         response.raise_for_status()
@@ -984,7 +994,7 @@ class HTTPHandler:
         params.update(self.extract_query_params(url))
 
         response = self.client.get(
-            url,
+            _parse_url(url),
             params=params,
             headers=headers,
         )
@@ -1023,10 +1033,11 @@ class HTTPHandler:
                 data, content
             )
 
+            parsed_url = _parse_url(url)
             if timeout is not None:
                 req = self.client.build_request(
                     "POST",
-                    url,
+                    parsed_url,
                     data=request_data,  # type: ignore
                     json=json,
                     params=params,
@@ -1037,7 +1048,7 @@ class HTTPHandler:
                 )
             else:
                 req = self.client.build_request(
-                    "POST", url, data=request_data, json=json, params=params, headers=headers, files=files, content=request_content  # type: ignore
+                    "POST", parsed_url, data=request_data, json=json, params=params, headers=headers, files=files, content=request_content  # type: ignore
                 )
             response = self.client.send(req, stream=stream)
             response.raise_for_status()
@@ -1079,13 +1090,14 @@ class HTTPHandler:
                 data, content
             )
 
+            parsed_url = _parse_url(url)
             if timeout is not None:
                 req = self.client.build_request(
-                    "PATCH", url, data=request_data, json=json, params=params, headers=headers, timeout=timeout, content=request_content  # type: ignore
+                    "PATCH", parsed_url, data=request_data, json=json, params=params, headers=headers, timeout=timeout, content=request_content  # type: ignore
                 )
             else:
                 req = self.client.build_request(
-                    "PATCH", url, data=request_data, json=json, params=params, headers=headers, content=request_content  # type: ignore
+                    "PATCH", parsed_url, data=request_data, json=json, params=params, headers=headers, content=request_content  # type: ignore
                 )
             response = self.client.send(req, stream=stream)
             response.raise_for_status()
@@ -1128,13 +1140,14 @@ class HTTPHandler:
                 data, content
             )
 
+            parsed_url = _parse_url(url)
             if timeout is not None:
                 req = self.client.build_request(
-                    "PUT", url, data=request_data, json=json, params=params, headers=headers, timeout=timeout, content=request_content  # type: ignore
+                    "PUT", parsed_url, data=request_data, json=json, params=params, headers=headers, timeout=timeout, content=request_content  # type: ignore
                 )
             else:
                 req = self.client.build_request(
-                    "PUT", url, data=request_data, json=json, params=params, headers=headers, content=request_content  # type: ignore
+                    "PUT", parsed_url, data=request_data, json=json, params=params, headers=headers, content=request_content  # type: ignore
                 )
             response = self.client.send(req, stream=stream)
             return response
@@ -1164,13 +1177,14 @@ class HTTPHandler:
                 data, content
             )
 
+            parsed_url = _parse_url(url)
             if timeout is not None:
                 req = self.client.build_request(
-                    "DELETE", url, data=request_data, json=json, params=params, headers=headers, timeout=timeout, content=request_content  # type: ignore
+                    "DELETE", parsed_url, data=request_data, json=json, params=params, headers=headers, timeout=timeout, content=request_content  # type: ignore
                 )
             else:
                 req = self.client.build_request(
-                    "DELETE", url, data=request_data, json=json, params=params, headers=headers, content=request_content  # type: ignore
+                    "DELETE", parsed_url, data=request_data, json=json, params=params, headers=headers, content=request_content  # type: ignore
                 )
             response = self.client.send(req, stream=stream)
             response.raise_for_status()

litellm/router.py

@@ -1314,9 +1314,10 @@ class Router:
 
     def print_deployment(self, deployment: dict):
         """
-        returns a copy of the deployment with the api key masked
+        Returns a lightweight dict with model_name + litellm_params (api key masked).
 
-        Only returns 2 characters of the api key and masks the rest with * (10 *).
+        Only includes model_name and litellm_params to avoid deep-copying
+        the full deployment dict on every log call.
         """
         try:
             litellm_params: dict = deployment.get("litellm_params", {})

tests/load_tests/run_perf_comparison.sh

@@ -84,7 +84,7 @@ PROXY_PID=$!
 wait_for_service "http://localhost:4000/health/liveliness" "LiteLLM Proxy (baseline)" 60
 
 echo "  Running baseline locust test..."
-cd "$WORKSPACE" && poetry run locust -f tests/load_tests/locustfile.py \
+cd "$WORKSPACE" && poetry run locust -f tests/load_tests/locustfile_perf.py \
     --headless -u "$USERS" -r "$SPAWN_RATE" --run-time "$DURATION" \
     --host http://localhost:4000 \
     --csv "$RESULTS_DIR/baseline" \
@@ -122,7 +122,7 @@ PROXY_PID=$!
 wait_for_service "http://localhost:4000/health/liveliness" "LiteLLM Proxy (optimized)" 60
 
 echo "  Running optimized locust test..."
-cd "$WORKSPACE" && poetry run locust -f tests/load_tests/locustfile.py \
+cd "$WORKSPACE" && poetry run locust -f tests/load_tests/locustfile_perf.py \
     --headless -u "$USERS" -r "$SPAWN_RATE" --run-time "$DURATION" \
     --host http://localhost:4000 \
     --csv "$RESULTS_DIR/optimized" \