diff --git a/tests/v1/tpu/worker/test_tpu_model_runner.py b/tests/v1/tpu/worker/test_tpu_model_runner.py
index e351f0e925250..73c0da45d4ab3 100644
--- a/tests/v1/tpu/worker/test_tpu_model_runner.py
+++ b/tests/v1/tpu/worker/test_tpu_model_runner.py
@@ -226,7 +226,7 @@ def test_update_states_request_resumed(model_runner):
         req_id=req_id,
         resumed_from_preemption=False,
         new_token_ids=[],
-        new_block_ids=[],
+        new_block_ids=[[]],
         num_computed_tokens=0,
     )
 
diff --git a/vllm/v1/worker/gpu_model_runner.py b/vllm/v1/worker/gpu_model_runner.py
index a90c294a97493..e3535ef143ada 100644
--- a/vllm/v1/worker/gpu_model_runner.py
+++ b/vllm/v1/worker/gpu_model_runner.py
@@ -460,8 +460,11 @@ class GPUModelRunner(LoRAModelRunnerMixin):
             # Update the block IDs.
             if not req_data.resumed_from_preemption:
                 # Append the new blocks to the existing block IDs.
-                for i in range(len(self.kv_cache_config.kv_cache_groups)):
-                    req_state.block_ids[i].extend(req_data.new_block_ids[i])
+                for block_ids, new_block_ids in zip(  # type: ignore[call-overload]
+                        req_state.block_ids,
+                        req_data.new_block_ids,
+                        strict=True):
+                    block_ids.extend(new_block_ids)
             else:
                 # The request is resumed from preemption.
                 # Replace the existing block IDs with the new ones.
diff --git a/vllm/v1/worker/tpu_model_runner.py b/vllm/v1/worker/tpu_model_runner.py
index 843bc36953b57..d5f40e4d3103c 100644
--- a/vllm/v1/worker/tpu_model_runner.py
+++ b/vllm/v1/worker/tpu_model_runner.py
@@ -413,7 +413,11 @@ class TPUModelRunner(LoRAModelRunnerMixin):
             req_state.num_computed_tokens = req_data.num_computed_tokens
             if not req_data.resumed_from_preemption:
                 # Append the new blocks to the existing block IDs.
-                req_state.block_ids.extend(req_data.new_block_ids)
+                for block_ids, new_block_ids in zip(  # type: ignore[call-overload]
+                        req_state.block_ids,
+                        req_data.new_block_ids,
+                        strict=True):
+                    block_ids.extend(new_block_ids)
             else:
                 # The request is resumed from preemption.
                 # Replace the existing block IDs with the new ones.