Skip to content

[None][ci] skip TestGPTOSS #7333

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
QiJune merged 2 commits into from
Aug 28, 2025
Merged

[None][ci] skip TestGPTOSS #7333

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8982ff3
fix mocker.patch.object error
QiJune Aug 28, 2025
72bf160
skip TestGPTOSS
QiJune Aug 28, 2025
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
6 changes: 4 additions & 2 deletions tests/integration/defs/accuracy/test_llm_api_pytorch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2719,6 +2719,7 @@ class TestGPTOSS(LlmapiAccuracyTestHarness):
(True, True),
])
def test_w4_1gpu(self, moe_backend, cuda_graph, overlap_scheduler, mocker):
pytest.skip("https://nvbugs/5481087")
if moe_backend == "TRITON" and not IS_TRITON_KERNELS_AVAILABLE:
pytest.skip("Triton kernels are not available")

Expand All @@ -2736,7 +2737,7 @@ def test_w4_1gpu(self, moe_backend, cuda_graph, overlap_scheduler, mocker):

with llm:
model_name = "GPT-OSS/MXFP4"
mocker.patch.object(GSM8K, {"MAX_OUTPUT_LEN": 8192})
mocker.patch.object(GSM8K, "MAX_OUTPUT_LEN", 8192)
task = GSM8K(model_name)
task.evaluate(llm,
extra_evaluator_kwargs=self.extra_evaluator_kwargs)
Expand All @@ -2756,6 +2757,7 @@ def test_w4_1gpu(self, moe_backend, cuda_graph, overlap_scheduler, mocker):
ids=["tp4", "ep4", "dp4"])
def test_w4_4gpus(self, moe_backend, tp_size, pp_size, ep_size,
attention_dp, cuda_graph, overlap_scheduler, mocker):
pytest.skip("https://nvbugs/5481087")
if moe_backend == "TRITON":
if not IS_TRITON_KERNELS_AVAILABLE:
pytest.skip("Triton kernels are not available")
Expand All @@ -2776,7 +2778,7 @@ def test_w4_4gpus(self, moe_backend, tp_size, pp_size, ep_size,
with llm:
model_name = "GPT-OSS/MXFP4"
task = GSM8K(model_name)
mocker.patch.object(GSM8K, {"MAX_OUTPUT_LEN": 8192})
mocker.patch.object(GSM8K, "MAX_OUTPUT_LEN", 8192)
task.evaluate(llm,
extra_evaluator_kwargs=self.extra_evaluator_kwargs)
Comment thread
QiJune marked this conversation as resolved.

Expand Down