Apply deepseek cuda rope (#5385)

Co-authored-by: Yineng Zhang <[email protected]>

Author: ispobock

python/sglang/srt/layers/rotary_embedding.py

@@ -645,7 +645,18 @@ def _compute_cos_sin_cache(self) -> torch.Tensor:
         cache = torch.cat((cos, sin), dim=-1)
         return cache
 
-    def forward(
+    def forward_hip(self, *args, **kwargs):
+        return self.forward_native(*args, **kwargs)
+
+    def forward(self, *args, **kwargs):
+        if torch._dynamo.is_compiling:
+            return self.forward_native(*args, **kwargs)
+        if _is_cuda_available:
+            return self.forward_cuda(*args, **kwargs)
+        else:
+            return self.forward_native(*args, **kwargs)
+
+    def forward_native(
         self,
         positions: torch.Tensor,
         query: torch.Tensor,