diff --git a/vllm/v1/worker/gpu_model_runner.py b/vllm/v1/worker/gpu_model_runner.py
index b1e4d04717768..978224faae65e 100644
--- a/vllm/v1/worker/gpu_model_runner.py
+++ b/vllm/v1/worker/gpu_model_runner.py
@@ -5074,7 +5074,6 @@ class GPUModelRunner(
                 logitsprocs_need_output_token_ids=self.input_batch.logitsprocs_need_output_token_ids,
                 is_pooling_model=self.is_pooling_model,
                 num_speculative_tokens=self.num_spec_tokens,
-                # sink_len=self.sink_len,
             )
 
     def _allocate_kv_cache_tensors(
diff --git a/vllm/v1/worker/kv_connector_model_runner_mixin.py b/vllm/v1/worker/kv_connector_model_runner_mixin.py
index f266a1386e10d..2bcc87b63bcdf 100644
--- a/vllm/v1/worker/kv_connector_model_runner_mixin.py
+++ b/vllm/v1/worker/kv_connector_model_runner_mixin.py
@@ -200,7 +200,7 @@ class KVConnectorModelRunnerMixin:
 
         try:
             kv_cache_stride_order = attn_backend.get_kv_cache_stride_order(
-                include_num_layers_dimension=True,
+                include_num_layers_dimension=True
             )
         except (AttributeError, NotImplementedError):
             return False
@@ -270,7 +270,7 @@ class KVConnectorModelRunnerMixin:
 
         try:
             kv_cache_stride_order = attn_backend.get_kv_cache_stride_order(
-                include_num_layers_dimension=True,
+                include_num_layers_dimension=True
             )
             assert len(kv_cache_stride_order) == len(kv_cache_shape)
         except (AttributeError, NotImplementedError):