From bca8222d02936f45b476c7b85f1be8db2f48af34 Mon Sep 17 00:00:00 2001
From: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
Date: Sun, 7 Dec 2025 02:44:58 -0800
Subject: [PATCH] move the rocketkv e2e test to post-merge.

Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
---
 tests/integration/defs/accuracy/references/longbench_v2.yaml | 2 +-
 tests/integration/defs/accuracy/test_llm_api_pytorch.py      | 2 +-
 tests/integration/test_lists/test-db/l0_b200.yml             | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/tests/integration/defs/accuracy/references/longbench_v2.yaml b/tests/integration/defs/accuracy/references/longbench_v2.yaml
index eae407f35a3..8f782aa4813 100644
--- a/tests/integration/defs/accuracy/references/longbench_v2.yaml
+++ b/tests/integration/defs/accuracy/references/longbench_v2.yaml
@@ -8,5 +8,5 @@ DeepSeek-R1-0528:
     spec_dec_algo: MTP
     accuracy: 52.093
 meta-llama/Llama-3.1-8B-Instruct:
-  - accuracy: 26.48
+  - accuracy: 26.00
     sigma: 25.8
diff --git a/tests/integration/defs/accuracy/test_llm_api_pytorch.py b/tests/integration/defs/accuracy/test_llm_api_pytorch.py
index f5396fc8a61..6edc2fd9000 100644
--- a/tests/integration/defs/accuracy/test_llm_api_pytorch.py
+++ b/tests/integration/defs/accuracy/test_llm_api_pytorch.py
@@ -4594,7 +4594,7 @@ def test_auto_dtype(self):
 
 
 @skip_pre_blackwell
-class TestLlama3_1_8B_Instruct_LongBenchV2(LlmapiAccuracyTestHarness):
+class TestLlama3_1_8B_Instruct_RocketKV(LlmapiAccuracyTestHarness):
     MODEL_NAME = "meta-llama/Llama-3.1-8B-Instruct"
     MODEL_PATH = f"{llm_models_root()}/llama-3.1-model/Llama-3.1-8B-Instruct/"
 
diff --git a/tests/integration/test_lists/test-db/l0_b200.yml b/tests/integration/test_lists/test-db/l0_b200.yml
index 4356e2601d1..fd04f2028e7 100644
--- a/tests/integration/test_lists/test-db/l0_b200.yml
+++ b/tests/integration/test_lists/test-db/l0_b200.yml
@@ -56,7 +56,6 @@ l0_b200:
   - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_w4a8_mxfp4[mxfp8-latency-CUTLASS]
   - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_w4a16_mxfp4[latency-TRTLLM]
   - accuracy/test_llm_api_pytorch.py::TestQwen3NextInstruct::test_nvfp4[tp1-cutlass]
-  - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8B_Instruct_LongBenchV2::test_auto_dtype
   - disaggregated/test_workers.py::test_workers_kv_cache_aware_router_eviction[TinyLlama-1.1B-Chat-v1.0] # nvbugs 5300551
   - test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-NVFP4-nvfp4-quantized/Meta-Llama-3.1-8B]
   - test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-FP8-llama-3.1-model/Llama-3.1-8B-Instruct-FP8]
@@ -157,3 +156,4 @@ l0_b200:
   - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=TRTLLM-mtp_nextn=2-fp8kv=False-attention_dp=False-cuda_graph=True-overlap_scheduler=False-torch_compile=False]
   - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTEDSL-mtp_nextn=0-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False]
   - accuracy/test_llm_api_pytorch.py::TestSeedOss_36B::test_auto_dtype
+  - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8B_Instruct_RocketKV::test_auto_dtype