feat - add debug_utils

litellm/proxy/common_utils/debug_utils.py

@@ -0,0 +1,27 @@
+# Start tracing memory allocations
+import os
+import tracemalloc
+
+from fastapi import APIRouter
+
+from litellm._logging import verbose_proxy_logger
+
+router = APIRouter()
+
+if os.environ.get("LITELLM_PROFILE", "false").lower() == "true":
+    tracemalloc.start()
+
+    @router.get("/memory-usage", include_in_schema=False)
+    async def memory_usage():
+        # Take a snapshot of the current memory usage
+        snapshot = tracemalloc.take_snapshot()
+        top_stats = snapshot.statistics("lineno")
+        verbose_proxy_logger.debug("TOP STATS: %s", top_stats)
+
+        # Get the top 50 memory usage lines
+        top_50 = top_stats[:50]
+        result = []
+        for stat in top_50:
+            result.append(f"{stat.traceback.format()}: {stat.size / 1024} KiB")
+
+        return {"top_50_memory_usage": result}

litellm/proxy/proxy_server.py

@@ -140,6 +140,7 @@ from litellm.proxy.auth.user_api_key_auth import user_api_key_auth
 
 ## Import All Misc routes here ##
 from litellm.proxy.caching_routes import router as caching_router
+from litellm.proxy.common_utils.debug_utils import router as debugging_endpoints_router
 from litellm.proxy.common_utils.http_parsing_utils import _read_request_body
 from litellm.proxy.health_check import perform_health_check
 from litellm.proxy.health_endpoints._health_endpoints import router as health_router
@@ -9173,3 +9174,4 @@ app.include_router(team_router)
 app.include_router(spend_management_router)
 app.include_router(caching_router)
 app.include_router(analytics_router)
+app.include_router(debugging_endpoints_router)