diff --git a/vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/kv_transfer.py b/vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/kv_transfer.py
index a7e570fa..a6df8c39 100644
--- a/vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/kv_transfer.py
+++ b/vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/kv_transfer.py
@@ -187,7 +187,7 @@ class KVCacheStoreSendingThread(KVTransferThread):
         ends = ends[skip_block_num:]
         keys = keys[skip_block_num:]
 
-        logger.info(
+        logger.debug(
             "Storing KV cache for %d out of %d blocks (skip_block_num=%d) for request %s",
             len(keys),
             token_len // self.block_size,
diff --git a/vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/pool_scheduler.py b/vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/pool_scheduler.py
index 2629b695..2796bfa0 100644
--- a/vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/pool_scheduler.py
+++ b/vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/pool_scheduler.py
@@ -91,7 +91,7 @@ class KVPoolScheduler:
         else:
             need_to_allocate = num_external_hit_tokens - num_computed_tokens
 
-        logger.info(
+        logger.debug(
             "Reqid: %s, Total tokens %d, kvpool hit tokens: %d, need to load: %d",
             request.request_id,
             request.num_tokens,