remove check for cuda

modeling_gemma.py

@@ -507,7 +507,7 @@ class GemmaSdpaAttention(GemmaAttention):
 
         # SDPA with memory-efficient backend is currently (torch==2.1.2) bugged with non-contiguous inputs with custom attn_mask,
         # Reference: https://github.com/pytorch/pytorch/issues/112577.
-        if query_states.device.type == "cuda" and causal_mask is not None:
+        if causal_mask is not None:
             query_states = query_states.contiguous()
             key_states = key_states.contiguous()
             value_states = value_states.contiguous()