diff --git a/tests/integration/test_lists/test-db/l0_b200.yml b/tests/integration/test_lists/test-db/l0_b200.yml index 64c762b5fa2..e51321d5b01 100644 --- a/tests/integration/test_lists/test-db/l0_b200.yml +++ b/tests/integration/test_lists/test-db/l0_b200.yml @@ -83,6 +83,7 @@ l0_b200: # ------------- AutoDeploy tests --------------- - unittest/_torch/auto_deploy/unit/singlegpu -k "not test_trtllm_bench_backend_comparison" - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[False-1] + - accuracy/test_llm_api_autodeploy.py::TestNemotronMOE::test_fp8 - unittest/_torch/auto_deploy/unit/singlegpu - condition: ranges: diff --git a/tests/integration/test_lists/test-db/l0_dgx_h200.yml b/tests/integration/test_lists/test-db/l0_dgx_h200.yml index a76555de7c5..efacea5814d 100644 --- a/tests/integration/test_lists/test-db/l0_dgx_h200.yml +++ b/tests/integration/test_lists/test-db/l0_dgx_h200.yml @@ -127,6 +127,7 @@ l0_dgx_h200: - disaggregated/test_disaggregated.py::test_disaggregated_benchmark_on_diff_backends[DeepSeek-V3-Lite-fp8] # ------------- AutoDeploy tests --------------- - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[False-4] + - accuracy/test_llm_api_autodeploy.py::TestNemotronMOE::test_bf16 - condition: ranges: system_gpu_count: diff --git a/tests/integration/test_lists/test-db/l0_h100.yml b/tests/integration/test_lists/test-db/l0_h100.yml index 6961d9a1ee7..9b1f97dc6d4 100644 --- a/tests/integration/test_lists/test-db/l0_h100.yml +++ b/tests/integration/test_lists/test-db/l0_h100.yml @@ -110,6 +110,8 @@ l0_h100: - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[True-1] - accuracy/test_llm_api_autodeploy.py::TestNemotronH::test_auto_dtype[False] - accuracy/test_llm_api_autodeploy.py::TestNemotronH::test_auto_dtype[True] + - accuracy/test_llm_api_autodeploy.py::TestNemotronMOE::test_fp8 + - accuracy/test_llm_api_autodeploy.py::TestNemotronMOE::test_bf16 - condition: ranges: system_gpu_count: