Skip to content

[None][infra] Update and waive failed tests for release branch #8291

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
EmmaQiaoCh merged 1 commit into from
Oct 12, 2025
Merged

[None][infra] Update and waive failed tests for release branch #8291

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 1 addition & 2 deletions tests/integration/test_lists/waives.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -339,9 +339,8 @@ unittest/_torch/multi_gpu_modeling/test_llama4.py::test_llama4[pp1-ep1-disable_a
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus_online_eplb[mtp_nextn=2] SKIP (https://nvbugs/5444687)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus_online_eplb[fp8kv=True] SKIP (https://nvbugs/5444687)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-pp4-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False] SKIP (https://nvbugs/5565604)
unittest/_torch/modules/test_fused_moe.py::test_fused_moe_fp8_blockwise_wide_ep[MNNVL] SKIP (https://nvbugs/5565565)
unittest/_torch/modules/test_fused_moe.py::test_fused_moe_fp8_blockwise_wide_ep[NotEnabled] SKIP (https://nvbugs/5565565)
unittest/_torch/multi_gpu_modeling/test_llama3.py::test_llama_3_3 SKIP (https://nvbugs/5565559)
disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_spec_dec_batch_slot_limit[False-False-EAGLE3-LLaMA3.1-Instruct-8B-Llama-3.1-8B-Instruct] SKIP (https://nvbugs/5565549)
accuracy/test_llm_api_pytorch.py::TestMistralSmall24B::test_auto_dtype SKIP (https://nvbugs/5565530)
accuracy/test_llm_api_pytorch.py::TestGemma3_27BInstruct::test_fp8_prequantized SKIP (https://nvbugs/5565521)
test_e2e.py::test_openai_chat_harmony SKIP (https://nvbugs/5575829)
1 change: 1 addition & 0 deletions tests/unittest/_torch/modules/test_fused_moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -639,6 +639,7 @@ def set_tensor_value_4(x, num_row, num_cols):
x.copy_(repeated)


@pytest.mark.skip(reason="https://nvbugs/5565565")
@skip_pre_blackwell
@pytest.mark.skipif(torch.cuda.device_count() < 4,
reason="needs 4 GPUs to run this test")
Expand Down
2 changes: 2 additions & 0 deletions tests/unittest/_torch/thop/parallel/test_moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -991,6 +991,7 @@ class TestMoeFp4:
the default tactic selection works. This reduces unnecessary test runs for CI
"""

@pytest.mark.skip(reason="https://nvbugs/5575841")
@pytest.mark.parametrize("num_tokens", [1, 1024])
@pytest.mark.parametrize("hidden_size", [1024])
@pytest.mark.parametrize("intermediate_size", [1024, 768, 384, 192])
Expand Down Expand Up @@ -1076,6 +1077,7 @@ def test_autotune(self, num_tokens, hidden_size, intermediate_size,
use_autotune=True,
use_topk_as_input=False)

@pytest.mark.skip(reason="https://nvbugs/5575841")
@pytest.mark.parametrize("num_tokens", [1, 150])
@pytest.mark.parametrize("hidden_size", [1024])
@pytest.mark.parametrize("intermediate_size", [1024])
Expand Down
Loading