From eb4ba1c2955c8cf949118c318581c1c3eeab70a2 Mon Sep 17 00:00:00 2001 From: maxiao1 Date: Wed, 29 Oct 2025 10:06:23 +0800 Subject: [PATCH] update UNBALANCED_MODEL_LOADING_TIMEOUT_S=3600 --- python/sglang/srt/model_executor/model_runner.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/sglang/srt/model_executor/model_runner.py b/python/sglang/srt/model_executor/model_runner.py index 601d36387..ce2a9c4c5 100644 --- a/python/sglang/srt/model_executor/model_runner.py +++ b/python/sglang/srt/model_executor/model_runner.py @@ -203,7 +203,7 @@ _is_xpu_xmx_available = xpu_has_xmx_support() SGLANG_CI_SMALL_KV_SIZE = os.getenv("SGLANG_CI_SMALL_KV_SIZE", None) # Detect stragger ranks in model loading -UNBALANCED_MODEL_LOADING_TIMEOUT_S = 36000 +UNBALANCED_MODEL_LOADING_TIMEOUT_S = 3600 # the ratio of mamba cache pool size to max_running_requests, it will be safe when it is larger than 2 (yizhang2077) MAMBA_CACHE_SIZE_MAX_RUNNING_REQUESTS_RATIO = 3