Skip to content

Commit 083f363

Browse files
authored
[https://nvbugs/5596343][test] Update test waive to get back some coverage (#8702)
Signed-off-by: Dongfeng Yu <[email protected]> Signed-off-by: dongfengy <[email protected]>
1 parent 0ee71d9 commit 083f363

File tree

2 files changed

+4
-2
lines changed

2 files changed

+4
-2
lines changed

tests/integration/defs/accuracy/test_llm_api_pytorch.py

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3465,7 +3465,6 @@ def test_dummy_load_format(self):
34653465
task = GSM8K(model_name)
34663466
task.evaluate(llm, is_integration_test=True)
34673467

3468-
@pytest.mark.skip(reason="https://nvbugs/5596343")
34693468
@pytest.mark.skip_less_device(4)
34703469
@pytest.mark.parametrize(
34713470
"kv_cache_dtype",
@@ -3485,6 +3484,10 @@ def test_dummy_load_format(self):
34853484
def test_w4_4gpus(self, kv_cache_dtype, moe_backend, tp_size, pp_size,
34863485
ep_size, attention_dp, cuda_graph, overlap_scheduler,
34873486
mocker):
3487+
if get_sm_version() < 100:
3488+
pytest.skip(
3489+
"https://nvbugs/5596343: Skip Hopper due to accuracy issue.")
3490+
34883491
mocker.patch.object(GSM8K, "MAX_OUTPUT_LEN", 8192)
34893492
mocker.patch.dict(GSM8K.EVALUATE_KWARGS,
34903493
{"scores_filter": "exact_match,flexible-extract"})

tests/integration/test_lists/waives.txt

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -330,7 +330,6 @@ cpp/test_e2e.py::test_benchmarks[gpt-80] SKIP (https://nvbugs/5550689)
330330
cpp/test_e2e.py::test_benchmarks[bart-90] SKIP (https://nvbugs/5550689)
331331
examples/test_nemotron_nas.py::test_nemotron_nano_8b_lora_torch[Llama-3.1-Nemotron-Nano-8B-v1] SKIP (https://nvbugs/5563469)
332332
test_e2e.py::test_ptp_quickstart_multimodal[qwen2-vl-7b-instruct-Qwen2-VL-7B-Instruct-image-False] SKIP (https://nvbugs/5547437)
333-
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-trtllm-auto] SKIP (https://nvbugs/5575913)
334333
accuracy/test_llm_api_pytorch.py::TestLlama4MaverickInstruct::test_fp8_eagle3[tp8-torch_compile=True] SKIP (https://nvbugs/5546510)
335334
test_e2e.py::test_multi_nodes_eval[Kimi-K2-Instruct-tp16-mmlu] SKIP (https://nvbugs/5556998)
336335
full:H20/accuracy/test_llm_api_pytorch.py::TestLlama4MaverickInstruct::test_fp8[tp8ep8-cuda_graph=True] SKIP (https://nvbugs/5574553)

0 commit comments

Comments
 (0)