diff --git a/tensorrt_llm/_torch/modules/fused_moe/fused_moe_cute_dsl.py b/tensorrt_llm/_torch/modules/fused_moe/fused_moe_cute_dsl.py
index 9b43f1b22b..9e5b2a1e94 100644
--- a/tensorrt_llm/_torch/modules/fused_moe/fused_moe_cute_dsl.py
+++ b/tensorrt_llm/_torch/modules/fused_moe/fused_moe_cute_dsl.py
@@ -34,7 +34,7 @@ def cute_dsl_fp8_group_blockwise_gemm_ref(
     b_tmp = b.permute(1, 2, 0)
 
     # Note: we have different output scale shape for fp8_quantize_1x128, so we need to handle it differently for sm100 and other archs.
-    if is_sm_100f() == 100:
+    if is_sm_100f():
         input_scale_tmp = a_sf.permute(1, 0).as_strided((m, w_k, 1),
                                                         (1, m, m * w_k))
     else:
diff --git a/tensorrt_llm/_torch/modules/fused_moe/quantization.py b/tensorrt_llm/_torch/modules/fused_moe/quantization.py
index 512c71d231..c8f30c8960 100644
--- a/tensorrt_llm/_torch/modules/fused_moe/quantization.py
+++ b/tensorrt_llm/_torch/modules/fused_moe/quantization.py
@@ -742,7 +742,7 @@ class DeepSeekFP8BlockScalesFusedMoEMethodDeepGemm(
 
     def load_weights(self, module: torch.nn.Module, weights: List[Dict],
                      weight_loading_mode: MoEWeightLoadingMode):
-        if is_sm_100f() == 100:
+        if is_sm_100f():
             expert_ids = set(module.initial_local_expert_ids)
             if self.need_load_shared_weights(module):
                 expert_ids.update(
@@ -759,7 +759,7 @@ class DeepSeekFP8BlockScalesFusedMoEMethodDeepGemm(
                         weight, scale)
         super().load_weights(module, weights, weight_loading_mode)
 
-        if is_sm_100f() == 100:
+        if is_sm_100f():
             transfromed_w3_w1_scale = transform_sf_into_required_layout(
                 module.quant_scales[0],
                 mn=module.w3_w1_weight.shape[1],