diff --git a/.gitmodules b/.gitmodules
index 45d99f8fe451..18f6d797b2d0 100644
--- a/.gitmodules
+++ b/.gitmodules
@@ -28,4 +28,5 @@
 	url = https://github.com/zeromq/cppzmq.git
 [submodule "3rdparty/DeepGEMM"]
 	path = 3rdparty/DeepGEMM
-	url = https://github.com/deepseek-ai/DeepGEMM.git
+	url = https://github.com/ruoqianguo/DeepGEMM.git
+	branch = dev/ruoqiang/swapab_sm100
diff --git a/tensorrt_llm/_torch/custom_ops/torch_custom_ops.py b/tensorrt_llm/_torch/custom_ops/torch_custom_ops.py
index 1dfc08620c42..e2c77cd4a81d 100644
--- a/tensorrt_llm/_torch/custom_ops/torch_custom_ops.py
+++ b/tensorrt_llm/_torch/custom_ops/torch_custom_ops.py
@@ -926,8 +926,9 @@ def get_valid_tactics(
         inputs: List[torch.Tensor],
         profile: OptimizationProfile,
     ) -> List[int]:
-        # Encode swap_ab as False (0) and True (1). Currently only add one tactic here.
-        return [0]
+        # Encode swap_ab as False (0) and True (1). Currently enabled when GEMM m <= 128.
+        input, _, _ = inputs
+        return [0, 1] if input.shape[0] <= 128 else [0]
 
     def forward(
         self,
@@ -941,9 +942,9 @@ def forward(
             device=input.device,
             dtype=self.output_dtype,
         )
-        # TODO: add swap_ab=tactic == 0 to detemrmine the swap_ab value
-        # Treat the default tactic=-1 as swap_ab=False
-        deep_gemm.fp8_gemm_nt(
+
+        forward_func = deep_gemm.fp8_gemm_ntt if tactic == 1 else deep_gemm.fp8_gemm_nt
+        forward_func(
             (a, a_sf),
             (weight, weight_scale),
             output,