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 d2384fba46..3a5e6ef6d6 100644 --- a/tests/integration/test_lists/test-db/l0_dgx_b200.yml +++ b/tests/integration/test_lists/test-db/l0_dgx_b200.yml @@ -40,9 +40,6 @@ l0_dgx_b200: - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[dep4_latency_moe_cutlass-torch_compile=False] - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[dep4_latency_moe_cutlass-torch_compile=True] ISOLATION - accuracy/test_llm_api_pytorch.py::TestQwen3NextThinking::test_auto_dtype[tp4ep4] - - accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_fp4[tp4-cuda_graph=True] - - accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_fp4[tp8ep8-cuda_graph=True] - - accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_fp8_chunked_prefill[tp4ep4-cuda_graph=True] - disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_fp8_ucx[DeepSeek-V3-Lite-fp8] - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-trtllm-auto] - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-cutlass-auto] @@ -173,6 +170,9 @@ l0_dgx_b200: - accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_auto_dtype[tp4ep4-cuda_graph=True] - accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_fp8[tp8ep8-cuda_graph=True] - accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_fp4_chunked_prefill[tp4ep4-cuda_graph=True] + - accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_fp4[tp4-cuda_graph=True] + - accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_fp4[tp8ep8-cuda_graph=True] + - accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_fp8_chunked_prefill[tp4ep4-cuda_graph=True] - accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_guided_decoding[xgrammar-mtp_nextn=0] - accuracy/test_disaggregated_serving.py::TestQwen3_30B_A3B::test_mixed_ctx_gen_model[ctxpp2gentp2] - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-cutlass-auto] diff --git a/tests/integration/test_lists/test-db/l0_dgx_b300.yml b/tests/integration/test_lists/test-db/l0_dgx_b300.yml index 7c60ea7ba6..69b1c1fa18 100644 --- a/tests/integration/test_lists/test-db/l0_dgx_b300.yml +++ b/tests/integration/test_lists/test-db/l0_dgx_b300.yml @@ -57,8 +57,6 @@ l0_dgx_b300: - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[tep4_latency_moe_cutlass-torch_compile=True] - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[dep4_latency_moe_trtllm-torch_compile=False] - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[dep4_latency_moe_cutlass-torch_compile=True] - - accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_fp8[tp4-cuda_graph=True] - - accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_fp4[tp4-cuda_graph=True] - accuracy/test_disaggregated_serving.py::TestQwen3_30B_A3B::test_mixed_ctx_gen_model[ctxpp2gentp2] - disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_fp8_ucx[DeepSeek-V3-Lite-fp8] - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-cutlass-fp8] diff --git a/tests/integration/test_lists/test-db/l0_h100.yml b/tests/integration/test_lists/test-db/l0_h100.yml index 67b30f0c30..39e92aafa5 100644 --- a/tests/integration/test_lists/test-db/l0_h100.yml +++ b/tests/integration/test_lists/test-db/l0_h100.yml @@ -75,7 +75,6 @@ l0_h100: - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_eagle3[enable_chunked_prefill=True-eagle3_one_model=False] - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_fp8_block_scales_cuda_graph_padding[mtp_nextn=0] - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_fp8_block_scales_cuda_graph_padding[mtp_nextn=2] - - test_e2e.py::test_trtllm_bench_pytorch_backend_sanity[meta-llama/Llama-3.1-8B-llama-3.1-8b-False-False] - test_e2e.py::test_trtllm_bench_pytorch_backend_sanity[meta-llama/Llama-3.1-8B-llama-3.1-8b-instruct-hf-fp8-True-True] - disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_fp8_tp1_single_gpu[DeepSeek-V3-Lite-fp8]