diff --git a/tests/integration/test_lists/qa/llm_function_core.txt b/tests/integration/test_lists/qa/llm_function_core.txt
index bfae8338be28..8cae573aeb30 100644
--- a/tests/integration/test_lists/qa/llm_function_core.txt
+++ b/tests/integration/test_lists/qa/llm_function_core.txt
@@ -505,11 +505,9 @@ accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[tp2-cutlass-auto]
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[tp2-triton-auto]
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[tp2-trtllm-auto]
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[tp2-trtllm-fp8]
-accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-dp4-cutlass-auto]
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-dp4-triton-auto]
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-dp4-trtllm-auto]
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-dp4-trtllm-fp8]
-accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-ep4-cutlass-auto]
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-ep4-triton-auto]
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-ep4-trtllm-auto]
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-ep4-trtllm-fp8]
diff --git a/tests/integration/test_lists/qa/llm_function_rtx6k.txt b/tests/integration/test_lists/qa/llm_function_rtx6k.txt
index 4260a5328d77..f23a801c914c 100644
--- a/tests/integration/test_lists/qa/llm_function_rtx6k.txt
+++ b/tests/integration/test_lists/qa/llm_function_rtx6k.txt
@@ -127,11 +127,9 @@ accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[tp2-cutlass-auto]
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[tp2-triton-auto]
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[tp2-trtllm-auto]
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[tp2-trtllm-fp8]
-accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-dp4-cutlass-auto]
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-dp4-triton-auto]
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-dp4-trtllm-auto]
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-dp4-trtllm-fp8]
-accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-ep4-cutlass-auto]
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-ep4-triton-auto]
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-ep4-trtllm-auto]
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-ep4-trtllm-fp8]
diff --git a/tests/integration/test_lists/test-db/l0_dgx_b200.yml b/tests/integration/test_lists/test-db/l0_dgx_b200.yml
index 77ca7e7f50bf..349550328fc7 100644
--- a/tests/integration/test_lists/test-db/l0_dgx_b200.yml
+++ b/tests/integration/test_lists/test-db/l0_dgx_b200.yml
@@ -325,7 +325,6 @@ l0_dgx_b200:
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-tp4-cutlass-auto]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-ep4-trtllm-auto]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-ep4-trtllm-fp8]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-dp4-cutlass-auto]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-ep4-trtllm-auto]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-ep4-trtllm-fp8]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-dp4-cutlass-auto]
diff --git a/tests/integration/test_lists/test-db/l0_dgx_h100.yml b/tests/integration/test_lists/test-db/l0_dgx_h100.yml
index 3cda7d22ca40..0269194d526e 100644
--- a/tests/integration/test_lists/test-db/l0_dgx_h100.yml
+++ b/tests/integration/test_lists/test-db/l0_dgx_h100.yml
@@ -253,9 +253,7 @@ l0_dgx_h100:
   tests:
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-tp4-cutlass-auto]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-tp4-triton-auto]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-ep4-cutlass-auto]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-ep4-triton-auto]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-dp4-cutlass-auto]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-dp4-triton-auto]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-ep4-cutlass-auto]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-ep4-triton-auto]
diff --git a/tests/integration/test_lists/test-db/l0_gb200_multi_gpus.yml b/tests/integration/test_lists/test-db/l0_gb200_multi_gpus.yml
index 0dd2d3935113..044926cd3f11 100644
--- a/tests/integration/test_lists/test-db/l0_gb200_multi_gpus.yml
+++ b/tests/integration/test_lists/test-db/l0_gb200_multi_gpus.yml
@@ -39,19 +39,13 @@ l0_gb200_multi_gpus:
   - accuracy/test_llm_api_pytorch.py::TestLlama3_3_70BInstruct::test_nvfp4_tp4[torch_compile=False]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_3_70BInstruct::test_nvfp4_tp4[torch_compile=True]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_3_70BInstruct::test_fp4_tp2pp2[torch_compile=True-enable_gemm_allreduce_fusion=False]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-tp4-trtllm-auto]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-dp4-cutlass-auto]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-tp4-trtllm-auto]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-dp4-cutlass-auto]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus_online_eplb[fp8]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-ep4-cutlass-auto]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-dp4-trtllm-fp8]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-ep4-cutlass-auto]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-dp4-trtllm-fp8]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4a16[dp4-fp8]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v1_kv_cache-cutlass-one_model-overlap_scheduler]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v2_kv_cache-cutlass-one_model-overlap_scheduler]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v1_kv_cache-trtllm-one_model-overlap_scheduler]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v2_kv_cache-trtllm-one_model-overlap_scheduler]
   - accuracy/test_llm_api_pytorch_multimodal.py::TestMistralLarge3_675B::test_nvfp4_4gpus[latency_moe_trtllm] TIMEOUT (90)
   - accuracy/test_disaggregated_serving.py::TestDeepSeekV4Flash::test_auto_dtype TIMEOUT (60)
@@ -125,7 +119,6 @@ l0_gb200_multi_gpus:
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[tp4-attn_backend=TRTLLM-torch_compile=True]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[tp4-attn_backend=FLASHINFER-torch_compile=False]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[pp4-attn_backend=TRTLLM-torch_compile=False]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-dp4-trtllm-auto]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-dp4-trtllm-auto]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4a16[dp4-auto]
   # ---- moved to post-merge (MoE CI optimization) ----
diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt
index 2180bc6f7bb3..980b720fd73a 100644
--- a/tests/integration/test_lists/waives.txt
+++ b/tests/integration/test_lists/waives.txt
@@ -62,8 +62,6 @@ accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backe
 accuracy/test_llm_api_pytorch.py::TestGLM52::test_nvfp4[tp_size=8-ep_size=8] SKIP (https://nvbugs/6507108)
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_guided_decoding_4gpus[one_model] SKIP (https://nvbugs/5596343)
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[v1_kv_cache-True-True-triton-auto] SKIP (https://nvbugs/6026676)
-accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-dp4-cutlass-auto] SKIP (https://nvbugs/6388142)
-accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-ep4-cutlass-auto] SKIP (https://nvbugs/5596343)
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-tp4-cutlass-auto] SKIP (https://nvbugs/5596343)
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-tp4-cutlass-fp8] SKIP (https://nvbugs/5651865)
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-dp4-cutlass-auto] SKIP (https://nvbugs/5596343)