Skip to content

[None][test] Update test case for release #10763

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
crazydemo merged 3 commits into from
Jan 19, 2026
Merged

[None][test] Update test case for release #10763

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a76f028
update test constraints
crazydemo Jan 16, 2026
1094dad
update interface
crazydemo Jan 16, 2026
0c3b44f
clean
crazydemo Jan 16, 2026
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
2 changes: 1 addition & 1 deletion tests/integration/defs/accuracy/accuracy_core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -452,7 +452,7 @@ class LongBenchV2(AccuracyTask):
EVALUATOR_KWARGS = dict(
dataset_path=DATASET_DIR,
length="medium",
max_len=120000,
max_input_length=120000,
apply_chat_template=True,
random_seed=0,
)
Expand Down
3 changes: 3 additions & 0 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 @@ -1118,6 +1118,7 @@ def test_fp8_prequantized(self):
task = MMLU(self.MODEL_NAME)
task.evaluate(llm)

@skip_pre_hopper
def test_fp8_vswa_reuse(self):
# NOTE: Test with VSWA kv cache config.
kv_cache_config = KvCacheConfig(
Expand All @@ -1132,6 +1133,7 @@ def test_fp8_vswa_reuse(self):
task = MMLU(self.MODEL_NAME)
task.evaluate(llm)

@skip_pre_hopper
@pytest.mark.parametrize("backend", ["xgrammar"])
def test_fp8_guided_decoding_vswa_reuse(self, backend: str, mocker):
mocker.patch.dict(os.environ, {"TRTLLM_XGUIDANCE_LENIENT": "1"})
Expand Down Expand Up @@ -5276,6 +5278,7 @@ class TestNemotronV3Nano(LlmapiAccuracyTestHarness):
EXTRA_EVALUATOR_KWARGS = dict(chat_template_kwargs=dict(
enable_thinking=False))

@pytest.mark.skip_less_device_memory(80000)
def test_auto_dtype(self):
with LLM(
f"{llm_models_root()}/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
Expand Down