From 5fc4b6004e848596d3b8729b9d47e36bdb12ac67 Mon Sep 17 00:00:00 2001
From: fzyzcjy <5236035+fzyzcjy@users.noreply.github.com>
Date: Mon, 21 Apr 2025 08:56:49 +0800
Subject: [PATCH] Add sanity check for max_running_requests (#5016)

---
 python/sglang/srt/managers/tp_worker.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/python/sglang/srt/managers/tp_worker.py b/python/sglang/srt/managers/tp_worker.py
index a79ea3281..fb3d1c6b4 100644
--- a/python/sglang/srt/managers/tp_worker.py
+++ b/python/sglang/srt/managers/tp_worker.py
@@ -116,6 +116,7 @@ class TpModelWorker:
             ),
             self.model_runner.req_to_token_pool.size,
         )
+        assert self.max_running_requests > 0, "max_running_request is zero"
         self.max_req_len = min(
             self.model_config.context_len - 1,
             self.max_total_num_tokens - 1,