[None][fix] fix post-merge issue raised by NVIDIA#5488

Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>

Author: nv-guomingz

tests/unittest/llmapi/test_executor.py

@@ -399,7 +399,7 @@ def test_ZeroMqQueue_serialization_complicated_dataclass():
     TokenRangeRetentionConfig = tllm.KvCacheRetentionConfig.TokenRangeRetentionConfig
     kvcache_config = tllm.KvCacheRetentionConfig(
         [TokenRangeRetentionConfig(0, 2, 30, datetime.timedelta(seconds=30))],
-        80)
+        80, None, tllm.KvCacheTransferMode.DRAM, "test_dir")
 
     sampling_params = SamplingParams(max_tokens=4,
                                      embedding_bias=torch.randn(2, 2))

tests/unittest/llmapi/test_llm.py

@@ -357,7 +357,7 @@ def test_llm_with_kv_cache_retention_config():
     kv_cache_retention_config = KvCacheRetentionConfig([
         KvCacheRetentionConfig.TokenRangeRetentionConfig(
             0, 2, 30, datetime.timedelta(seconds=30))
-    ], 80)
+    ], 80, None, tllm.KvCacheTransferMode.DRAM, "test_dir")
 
     llm = LLM(model=llama_model_path,
               kv_cache_config=global_kvcache_config,