diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt
index 35dcc590144..36105b1ba7a 100644
--- a/tests/integration/test_lists/waives.txt
+++ b/tests/integration/test_lists/waives.txt
@@ -432,3 +432,4 @@ triton_server/test_triton_llm.py::test_gpt_disaggregated_serving_bls[test_basic-
 triton_server/test_triton.py::test_gpt_disaggregated_serving_bls[gpt-disaggregated-serving-bls] SKIP (https://nvbugs/5401261)
 examples/test_recurrentgemma.py::test_llm_recurrentgemma_2gpu[recurrentgemma-2b] SKIP (https://nvbugs/5401233)
 examples/test_multimodal.py::test_llm_multimodal_general[VILA1.5-3b-pp:1-tp:1-float16-bs:1-cpp_e2e:False-nb:1] SKIP (https://nvbugs/5401156)
+test_e2e.py::test_ptp_quickstart_multimodal[mistral-small-3.1-24b-instruct-Mistral-Small-3.1-24B-Instruct-2503-image-True] SKIP (https://nvbugs/5404005)
diff --git a/tests/unittest/_torch/modeling/test_modeling_nemotron_h.py b/tests/unittest/_torch/modeling/test_modeling_nemotron_h.py
index 14c300c372a..a95a60889f1 100644
--- a/tests/unittest/_torch/modeling/test_modeling_nemotron_h.py
+++ b/tests/unittest/_torch/modeling/test_modeling_nemotron_h.py
@@ -1,3 +1,4 @@
+import pytest
 import torch
 from utils.llm_data import llm_models_root
 from utils.util import skip_gpu_memory_less_than
@@ -237,6 +238,7 @@ def test_nemotron_h_correctness():
         nemotron_h.shutdown()
 
 
+@pytest.mark.skip(reason="https://nvbugs/5404046")
 def test_nemotron_h_cuda_graph_overlap_scheduler():
     prompts = [
         "Tell me something I don't know about the future of AI",