From 2a39cfe0fffbe303be67f1b424c40f56d3084bec Mon Sep 17 00:00:00 2001 From: Chunyuan WU Date: Sat, 13 Dec 2025 13:32:19 +0800 Subject: [PATCH] call check_quantized_moe_compatibility after initialize (#13876) --- 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 dbbf6e66d..81d2dd86b 100644 --- a/python/sglang/srt/model_executor/model_runner.py +++ b/python/sglang/srt/model_executor/model_runner.py @@ -323,7 +323,6 @@ class ModelRunner: # Model-specific adjustment self.model_specific_adjustment() - self.check_quantized_moe_compatibility() # Set the global server_args in the scheduler process set_global_server_args_for_scheduler(server_args) @@ -355,6 +354,7 @@ class ModelRunner: # Initialize the model runner self.initialize(min_per_gpu_memory) + self.check_quantized_moe_compatibility() # Temporary cached values self.support_pp = (