diff --git a/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json b/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json
index abf258e56..bb17743b6 100644
--- a/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json
+++ b/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json
@@ -55,35 +55,35 @@
         "kpack": 2
     },
     "128": {
-        "BLOCK_SIZE_M": 16,
-        "BLOCK_SIZE_N": 64,
-        "BLOCK_SIZE_K": 256,
+        "BLOCK_SIZE_M": 64,
+        "BLOCK_SIZE_N": 128,
+        "BLOCK_SIZE_K": 128,
         "GROUP_SIZE_M": 1,
-        "num_warps": 4,
+        "num_warps": 8,
         "num_stages": 0,
-        "waves_per_eu": 1,
+        "waves_per_eu": 0,
         "matrix_instr_nonkdim": 16,
         "kpack": 1
     },
     "256": {
-        "BLOCK_SIZE_M": 16,
-        "BLOCK_SIZE_N": 64,
-        "BLOCK_SIZE_K": 256,
+        "BLOCK_SIZE_M": 64,
+        "BLOCK_SIZE_N": 128,
+        "BLOCK_SIZE_K": 128,
         "GROUP_SIZE_M": 1,
-        "num_warps": 4,
+        "num_warps": 8,
         "num_stages": 0,
-        "waves_per_eu": 1,
+        "waves_per_eu": 0,
         "matrix_instr_nonkdim": 16,
         "kpack": 1
     },
     "512": {
         "BLOCK_SIZE_M": 64,
-        "BLOCK_SIZE_N": 64,
-        "BLOCK_SIZE_K": 256,
+        "BLOCK_SIZE_N": 128,
+        "BLOCK_SIZE_K": 128,
         "GROUP_SIZE_M": 1,
-        "num_warps": 4,
+        "num_warps": 8,
         "num_stages": 0,
-        "waves_per_eu": 2,
+        "waves_per_eu": 0,
         "matrix_instr_nonkdim": 16,
         "kpack": 2
     },