diff --git a/vllm/entrypoints/serve/instrumentator/server_info.py b/vllm/entrypoints/serve/instrumentator/server_info.py
index 6ba92d5b9..d6ef994f3 100644
--- a/vllm/entrypoints/serve/instrumentator/server_info.py
+++ b/vllm/entrypoints/serve/instrumentator/server_info.py
@@ -2,6 +2,8 @@
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 
+import asyncio
+import functools
 from typing import Annotated, Literal
 
 import pydantic
@@ -9,6 +11,7 @@ from fastapi import APIRouter, FastAPI, Query, Request
 from fastapi.responses import JSONResponse
 
 import vllm.envs as envs
+from vllm.collect_env import get_env_info
 from vllm.config import VllmConfig
 from vllm.logger import init_logger
 
@@ -32,6 +35,11 @@ def _get_vllm_env_vars():
     return vllm_envs
 
 
+@functools.lru_cache(maxsize=1)
+def _get_system_env_info_cached():
+    return get_env_info()._asdict()
+
+
 @router.get("/server_info")
 async def show_server_info(
     raw_request: Request,
@@ -46,6 +54,7 @@ async def show_server_info(
         ),
         # fallback=str is needed to handle e.g. torch.dtype
         "vllm_env": _get_vllm_env_vars(),
+        "system_env": await asyncio.to_thread(_get_system_env_info_cached),
     }
     return JSONResponse(content=server_info)