From cee93a6f26023d978b5187725bcb3c15ba604343 Mon Sep 17 00:00:00 2001 From: Alison Shao <54658187+alisonshao@users.noreply.github.com> Date: Sat, 6 Dec 2025 11:34:03 -0800 Subject: [PATCH] [Bug fix] Add /model_info endpoint to mini_lb (#14535) --- .../bindings/python/sglang_router/mini_lb.py | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/sgl-model-gateway/bindings/python/sglang_router/mini_lb.py b/sgl-model-gateway/bindings/python/sglang_router/mini_lb.py index 7c3089b5e..39e809358 100644 --- a/sgl-model-gateway/bindings/python/sglang_router/mini_lb.py +++ b/sgl-model-gateway/bindings/python/sglang_router/mini_lb.py @@ -341,8 +341,7 @@ async def get_server_info(): } -@app.get("/get_model_info") -async def get_model_info(): +async def _get_model_info_impl(): if not lb or not lb.prefill_urls: raise HTTPException( status_code=HTTPStatus.SERVICE_UNAVAILABLE, @@ -350,7 +349,7 @@ async def get_model_info(): ) target_server_url = lb.prefill_urls[0] - endpoint_url = f"{target_server_url}/get_model_info" + endpoint_url = f"{target_server_url}/model_info" async with aiohttp.ClientSession() as session: try: @@ -375,6 +374,16 @@ async def get_model_info(): ) +@app.get("/model_info") +async def model_info(): + return await _get_model_info_impl() + + +@app.get("/get_model_info") +async def get_model_info(): + return await _get_model_info_impl() + + @app.post("/generate") async def handle_generate_request(request_data: dict): prefill_server, bootstrap_port, decode_server = lb.select_pair()