diff --git a/tests/v1/tpu/test_pallas.py b/tests/v1/tpu/test_pallas.py
index e279edfff..df8913317 100644
--- a/tests/v1/tpu/test_pallas.py
+++ b/tests/v1/tpu/test_pallas.py
@@ -50,6 +50,7 @@ def test_ragged_paged_attention():
     slot_mapping = torch.zeros((3, num_tokens), dtype=torch.int64)
     max_num_reqs = 8
     max_num_blocks_per_req = 8
+    num_kv_update_slices = torch.tensor([num_tokens], dtype=torch.int32)
     block_tables = torch.zeros((max_num_reqs, max_num_blocks_per_req),
                                dtype=torch.int32)
     context_lens = torch.ones((max_num_reqs, ), dtype=torch.int32)
@@ -65,6 +66,7 @@ def test_ragged_paged_attention():
         context_lens=context_lens,
         query_start_loc=query_start_loc,
         num_seqs=num_seqs,
+        num_kv_update_slices=num_kv_update_slices,
         num_slices_per_kv_cache_update_block=8,
     )