diff --git a/vllm/worker/hpu_enc_dec_model_runner.py b/vllm/worker/hpu_enc_dec_model_runner.py
index 2b0c684d16c9f..2b8acb502822d 100644
--- a/vllm/worker/hpu_enc_dec_model_runner.py
+++ b/vllm/worker/hpu_enc_dec_model_runner.py
@@ -332,6 +332,15 @@ def _prepare_encoder_model_input_tensors(
             attn_metadata.cross_block_groups = block_groups
             attn_metadata.cross_block_usage = block_usage
 
+        # add padding to align with language model shapes
+        real_batch_size = len(seq_group_metadata_list)
+        batch_size_padded = self.bucketing_ctx.get_padded_batch_size(
+            real_batch_size, is_prompt)
+        batch_size_padding = batch_size_padded - real_batch_size
+        if batch_size_padding > 0:
+            encoder_seq_lens.extend(encoder_seq_lens[0]
+                                    for _ in range(batch_size_padding))
+
         encoder_seq_lens_tensor = self._list_to_int32_tensor(encoder_seq_lens)
         attn_metadata.encoder_seq_lens = encoder_seq_lens
         attn_metadata.encoder_seq_lens_tensor = encoder_seq_lens_tensor