kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[TRTLLM-7250][fix] waive failed cases (#7292)

Browse Source 
Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>
This commit is contained in:
xinhe-nv 2025-08-27 18:04:46 +08:00 committed by GitHub
parent 8b216135f0
commit f082e4857c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 37 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
tests/integration/defs/accuracy/test_llm_api_pytorch.py
View File

@ -2697,6 +2697,8 @@ class TestPhi4MM(LlmapiAccuracyTestHarness):
task.evaluate(llm)
@skip_pre_hopper
@pytest.mark.skip_less_device_memory(100000)
class TestGPTOSS(LlmapiAccuracyTestHarness):
kv_cache_config = KvCacheConfig(free_gpu_memory_fraction=0.5)
extra_evaluator_kwargs = {
@ -2708,8 +2710,11 @@ class TestGPTOSS(LlmapiAccuracyTestHarness):
MODEL_PATH = f"{llm_models_root()}/gpt_oss/gpt-oss-120b"
@pytest.mark.parametrize("moe_backend", ["CUTLASS", "TRTLLM", "TRITON"],
ids=["cutlass", "trtllm", "triton"])
@pytest.mark.parametrize(
"moe_backend",
["CUTLASS",
pytest.param("TRTLLM", marks=skip_pre_blackwell), "TRITON"],
ids=["cutlass", "trtllm", "triton"])
@pytest.mark.parametrize("cuda_graph,overlap_scheduler", [
(True, True),
])
@ -2737,7 +2742,11 @@ class TestGPTOSS(LlmapiAccuracyTestHarness):
extra_evaluator_kwargs=self.extra_evaluator_kwargs)
@pytest.mark.skip_less_device(4)
@pytest.mark.parametrize("moe_backend", ["CUTLASS", "TRTLLM", "TRITON"])
@pytest.mark.parametrize(
"moe_backend",
["CUTLASS",
pytest.param("TRTLLM", marks=skip_pre_blackwell), "TRITON"],
ids=["cutlass", "trtllm", "triton"])
@pytest.mark.parametrize(
"tp_size,pp_size,ep_size,attention_dp,cuda_graph,overlap_scheduler", [
(4, 1, 1, False, True, True),

18
tests/integration/test_lists/qa/llm_function_full.txt
View File

@ -539,15 +539,15 @@ accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_w4a16_mxfp4[latency-TR
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-cutlass]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-trtllm]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-triton]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-CUTLASS]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-TRTLLM]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-TRITON]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-CUTLASS]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-TRTLLM]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-TRITON]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-CUTLASS]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-TRTLLM]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-TRITON]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-cutlass]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-trtllm]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-triton]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-cutlass]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-trtllm]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-triton]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-cutlass]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-trtllm]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-triton]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4a16[dp4]
accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_auto_dtype[False]
accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_auto_dtype[True]

18
tests/integration/test_lists/qa/llm_function_sanity.txt
View File

@ -48,15 +48,15 @@ accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-cutlass]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-triton]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-trtllm]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-CUTLASS]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-TRITON]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-TRTLLM]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-CUTLASS]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-TRITON]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-TRTLLM]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-CUTLASS]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-TRITON]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-TRTLLM]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-cutlass]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-triton]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-trtllm]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-cutlass]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-triton]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-trtllm]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-cutlass]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-triton]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-trtllm]
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4a16[dp4]
accuracy/test_llm_api_pytorch.py::TestKanana_Instruct::test_auto_dtype
accuracy/test_llm_api_pytorch.py::TestKimiK2::test_fp8_blockscale[latency]

14
tests/integration/test_lists/waives.txt
View File

@ -337,15 +337,15 @@ accuracy/test_cli_flow.py::TestLongAlpaca7B::test_auto_dtype SKIP (https://nvbug
accuracy/test_llm_api.py::TestPhi4MiniInstruct::test_fp8 SKIP (https://nvbugs/5465143)
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_fp8_blockscale[throughput] SKIP (https://nvbugs/5471106)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-cutlass] SKIP (https://nvbugs/5481080)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-trtllm] SKIP (https://nvbugs/5481087)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-CUTLASS] SKIP (https://nvbugs/5481080)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-TRTLLM] SKIP (https://nvbugs/5481087)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-CUTLASS] SKIP (https://nvbugs/5481080)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-TRTLLM] SKIP (https://nvbugs/5481087)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-CUTLASS] SKIP (https://nvbugs/5481080)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-TRTLLM] SKIP (https://nvbugs/5481087)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-cutlass] SKIP (https://nvbugs/5481080)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-cutlass] SKIP (https://nvbugs/5481080)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-cutlass] SKIP (https://nvbugs/5481080)
accuracy/test_llm_api_pytorch.py::TestEXAONE4::test_auto_dtype SKIP (https://nvbugs/5481090)
test_e2e.py::test_ptp_quickstart_advanced_8gpus_chunked_prefill_sq_22k[Llama-4-Maverick-17B-128E-Instruct-FP8-llama4-models/nvidia/Llama-4-Maverick-17B-128E-Instruct-FP8-False] SKIP (https://nvbugs/5481094)
test_e2e.py::test_ptp_quickstart_advanced_8gpus_chunked_prefill_sq_22k[Llama-4-Maverick-17B-128E-Instruct-FP8-llama4-models/nvidia/Llama-4-Maverick-17B-128E-Instruct-FP8-True] SKIP (https://nvbugs/5481094)
test_e2e.py::test_ptp_quickstart_advanced_8gpus_chunked_prefill_sq_22k[Llama-4-Scout-17B-16E-Instruct-FP8-llama4-models/Llama-4-Scout-17B-16E-Instruct-FP8-True] SKIP (https://nvbugs/5481094)
test_e2e.py::test_ptp_quickstart_multimodal_2gpu[Phi-4-multimodal-instruct-multimodals/Phi-4-multimodal-instruct] SKIP (https://nvbugs/5480415)
accuracy/test_llm_api_pytorch.py::TestLlama4MaverickInstruct::test_fp8_eagle3[tp8-torch_compile=False] SKIP (https://nvbugs/5483534)
accuracy/test_llm_api_pytorch.py::TestLlama4MaverickInstruct::test_fp8_eagle3[tp8-torch_compile=True] SKIP (https://nvbugs/5483615)
accuracy/test_disaggregated_serving.py::TestQwen3_8B::test_nixl_backend SKIP (https://nvbugs/5448748)
accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_nixl_backend SKIP (https://nvbugs/5448748)