From adfb17fee36833cccb37585aca588cd771e22641 Mon Sep 17 00:00:00 2001
From: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Date: Thu, 30 Jul 2026 14:21:22 +0800
Subject: [PATCH] [https://nvbugs/6528742][test] Disable V2 in legacy Mamba
 test (By Agent)

Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
---
 tests/integration/defs/accuracy/test_llm_api_pytorch.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tests/integration/defs/accuracy/test_llm_api_pytorch.py b/tests/integration/defs/accuracy/test_llm_api_pytorch.py
index ad192d34d9a5..b7b774e48911 100644
--- a/tests/integration/defs/accuracy/test_llm_api_pytorch.py
+++ b/tests/integration/defs/accuracy/test_llm_api_pytorch.py
@@ -7115,6 +7115,7 @@ def test_fp8_4gpus(self, attention_dp, use_cpp_mamba, monkeypatch):
                     enable_block_reuse=False,
                     mamba_ssm_cache_dtype="float16",
                     free_gpu_memory_fraction=0.5,
+                    use_kv_cache_manager_v2=False,
                 ),
                 max_batch_size=32,
                 tensor_parallel_size=4,