diff --git a/src/transformers/models/deepseekv3/modeling_deepseekv3.py b/src/transformers/models/deepseekv3/modeling_deepseekv3.py
index 9c00887e3..b9c0bb928 100644
--- a/src/transformers/models/deepseekv3/modeling_deepseekv3.py
+++ b/src/transformers/models/deepseekv3/modeling_deepseekv3.py
@@ -368,16 +368,16 @@ def rotate_half(x):
 
 
 # Copied from transformers.models.llama.modeling_llama.apply_rotary_pos_emb
-def apply_rotary_pos_emb(q, k, cos, sin, position_ids, unsqueeze_dim=1):
+def apply_rotary_pos_emb(q, k, cos, sin, position_ids=None, unsqueeze_dim=1):
     """Applies Rotary Position Embedding to the query and key tensors.
+
     Args:
         q (`torch.Tensor`): The query tensor.
         k (`torch.Tensor`): The key tensor.
         cos (`torch.Tensor`): The cosine part of the rotary embedding.
         sin (`torch.Tensor`): The sine part of the rotary embedding.
-        position_ids (`torch.Tensor`):
-            The position indices of the tokens corresponding to the query and key tensors. For example, this can be
-            used to pass offsetted position ids when working with a KV-cache.
+        position_ids (`torch.Tensor`, *optional*):
+            Deprecated and unused.
         unsqueeze_dim (`int`, *optional*, defaults to 1):
             The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
             sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
@@ -388,15 +388,8 @@ def apply_rotary_pos_emb(q, k, cos, sin, position_ids, unsqueeze_dim=1):
     Returns:
         `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
     """
-    cos = cos[position_ids].unsqueeze(unsqueeze_dim)
-    sin = sin[position_ids].unsqueeze(unsqueeze_dim)
-
-    b, h, s, d = q.shape
-    q = q.view(b, h, s, d // 2, 2).transpose(4, 3).reshape(b, h, s, d)
-
-    b, h, s, d = k.shape
-    k = k.view(b, h, s, d // 2, 2).transpose(4, 3).reshape(b, h, s, d)
-
+    cos = cos.unsqueeze(unsqueeze_dim)
+    sin = sin.unsqueeze(unsqueeze_dim)
     q_embed = (q * cos) + (rotate_half(q) * sin)
     k_embed = (k * cos) + (rotate_half(k) * sin)
     return q_embed, k_embed
diff --git a/src/transformers/models/deepseekv3/modular_deepseekv3.py b/src/transformers/models/deepseekv3/modular_deepseekv3.py
index cba30e878..de401b6e4 100644
--- a/src/transformers/models/deepseekv3/modular_deepseekv3.py
+++ b/src/transformers/models/deepseekv3/modular_deepseekv3.py
@@ -47,16 +47,16 @@ def rotate_half(x):
 
 
 # Copied from transformers.models.llama.modeling_llama.apply_rotary_pos_emb
-def apply_rotary_pos_emb(q, k, cos, sin, position_ids, unsqueeze_dim=1):
+def apply_rotary_pos_emb(q, k, cos, sin, position_ids=None, unsqueeze_dim=1):
     """Applies Rotary Position Embedding to the query and key tensors.
+
     Args:
         q (`torch.Tensor`): The query tensor.
         k (`torch.Tensor`): The key tensor.
         cos (`torch.Tensor`): The cosine part of the rotary embedding.
         sin (`torch.Tensor`): The sine part of the rotary embedding.
-        position_ids (`torch.Tensor`):
-            The position indices of the tokens corresponding to the query and key tensors. For example, this can be
-            used to pass offsetted position ids when working with a KV-cache.
+        position_ids (`torch.Tensor`, *optional*):
+            Deprecated and unused.
         unsqueeze_dim (`int`, *optional*, defaults to 1):
             The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
             sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
@@ -67,15 +67,8 @@ def apply_rotary_pos_emb(q, k, cos, sin, position_ids, unsqueeze_dim=1):
     Returns:
         `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
     """
-    cos = cos[position_ids].unsqueeze(unsqueeze_dim)
-    sin = sin[position_ids].unsqueeze(unsqueeze_dim)
-
-    b, h, s, d = q.shape
-    q = q.view(b, h, s, d // 2, 2).transpose(4, 3).reshape(b, h, s, d)
-
-    b, h, s, d = k.shape
-    k = k.view(b, h, s, d // 2, 2).transpose(4, 3).reshape(b, h, s, d)
-
+    cos = cos.unsqueeze(unsqueeze_dim)
+    sin = sin.unsqueeze(unsqueeze_dim)
     q_embed = (q * cos) + (rotate_half(q) * sin)
     k_embed = (k * cos) + (rotate_half(k) * sin)
     return q_embed, k_embed