diff --git a/python/sglang/srt/models/deepseek_v2.py b/python/sglang/srt/models/deepseek_v2.py
index ea8ec92a5..ab67e03a6 100644
--- a/python/sglang/srt/models/deepseek_v2.py
+++ b/python/sglang/srt/models/deepseek_v2.py
@@ -3292,10 +3292,8 @@ class DeepseekV2ForCausalLM(nn.Module):
                 "Only Deepseek V3/R1 on NV-platform with capability >= 80 "
                 "or AMD-platform with capability >= gfx942(MI30x) can use shared experts fusion optimization."
             )
-        elif (
-            get_moe_expert_parallel_world_size() > 1
-            and _is_hip
-            and torch.cuda.get_device_capability("cuda") < (9, 4)
+        elif get_moe_expert_parallel_world_size() > 1 and (
+            not _is_hip or torch.cuda.get_device_capability("cuda") < (9, 4)
         ):
             disable_reason = "Only Deepseek V3/R1 on AMD-platform with capability >= gfx942(MI30x) can use shared experts fusion optimization under expert parallelism."
         elif disable_reason is None and get_moe_a2a_backend().is_deepep():