kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-19 01:05:12 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[https://nvbugs/5596343][test] Update test waive to get back some coverage (#8702)

Browse Source 
Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
Signed-off-by: dongfengy <99041270+dongfengy@users.noreply.github.com>
This commit is contained in:
dongfengy 2025-10-28 14:05:48 -07:00 committed by GitHub
parent 0ee71d95ec
commit 083f3637f1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
tests/integration/defs/accuracy/test_llm_api_pytorch.py
View File

@ -3465,7 +3465,6 @@ class TestGPTOSS(LlmapiAccuracyTestHarness):
task = GSM8K(model_name)
task.evaluate(llm, is_integration_test=True)
@pytest.mark.skip(reason="https://nvbugs/5596343")
@pytest.mark.skip_less_device(4)
@pytest.mark.parametrize(
"kv_cache_dtype",
@ -3485,6 +3484,10 @@ class TestGPTOSS(LlmapiAccuracyTestHarness):
def test_w4_4gpus(self, kv_cache_dtype, moe_backend, tp_size, pp_size,
ep_size, attention_dp, cuda_graph, overlap_scheduler,
mocker):
if get_sm_version() < 100:
pytest.skip(
"https://nvbugs/5596343: Skip Hopper due to accuracy issue.")
mocker.patch.object(GSM8K, "MAX_OUTPUT_LEN", 8192)
mocker.patch.dict(GSM8K.EVALUATE_KWARGS,
{"scores_filter": "exact_match,flexible-extract"})

1
tests/integration/test_lists/waives.txt
View File

@ -330,7 +330,6 @@ cpp/test_e2e.py::test_benchmarks[gpt-80] SKIP (https://nvbugs/5550689)
cpp/test_e2e.py::test_benchmarks[bart-90] SKIP (https://nvbugs/5550689)
examples/test_nemotron_nas.py::test_nemotron_nano_8b_lora_torch[Llama-3.1-Nemotron-Nano-8B-v1] SKIP (https://nvbugs/5563469)
test_e2e.py::test_ptp_quickstart_multimodal[qwen2-vl-7b-instruct-Qwen2-VL-7B-Instruct-image-False] SKIP (https://nvbugs/5547437)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-trtllm-auto] SKIP (https://nvbugs/5575913)
accuracy/test_llm_api_pytorch.py::TestLlama4MaverickInstruct::test_fp8_eagle3[tp8-torch_compile=True] SKIP (https://nvbugs/5546510)
test_e2e.py::test_multi_nodes_eval[Kimi-K2-Instruct-tp16-mmlu] SKIP (https://nvbugs/5556998)
full:H20/accuracy/test_llm_api_pytorch.py::TestLlama4MaverickInstruct::test_fp8[tp8ep8-cuda_graph=True] SKIP (https://nvbugs/5574553)