diff --git a/benchmark/kernels/fused_moe_triton/README.md b/benchmark/kernels/fused_moe_triton/README.md
index 573e0ffaa..48598854a 100644
--- a/benchmark/kernels/fused_moe_triton/README.md
+++ b/benchmark/kernels/fused_moe_triton/README.md
@@ -42,7 +42,7 @@ python benchmark/kernels/fused_moe_triton/tuning_fused_moe_triton.py \
     --tune
 ```
 
-After tuning, a configuration file (e.g., `E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json`) will be generated in the current directory. You can move this file to `sglang/srt/layers/fused_moe_triton/configs/` to use it in `sglang`.
+After tuning, a configuration file (e.g., `E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json`) will be generated in the current directory. You can move this file to `sglang/srt/layers/fused_moe_triton/configs/triton_version` dir to use it in `sglang`.
 
 ### Performance Comparison Tool
 
diff --git a/python/sglang/srt/layers/moe/fused_moe_triton/configs/README b/python/sglang/srt/layers/moe/fused_moe_triton/configs/README.md
similarity index 100%
rename from python/sglang/srt/layers/moe/fused_moe_triton/configs/README
rename to python/sglang/srt/layers/moe/fused_moe_triton/configs/README.md
diff --git a/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=257,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json b/python/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json
similarity index 100%
rename from python/sglang/srt/layers/moe/fused_moe_triton/configs/E=257,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json
rename to python/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json
diff --git a/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=257,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json b/python/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json
similarity index 100%
rename from python/sglang/srt/layers/moe/fused_moe_triton/configs/E=257,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json
rename to python/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json