enable 2 llama UT cases on xpu (#37126)

* enable tests/models/llama/test_modeling_llama.py::LlamaIntegrationTest::test_model_7b_logits and tests/models/llama/test_modeling_llama.py::LlamaIntegrationTest::test_model_7b_logits_bf16 on xpu

Signed-off-by: YAO Matrix <matrix.yao@intel.com>

* switch to use Expectations

Signed-off-by: YAO Matrix <matrix.yao@intel.com>

* fix style

Signed-off-by: YAO Matrix <matrix.yao@intel.com>

* extract gen bits from architecture and use it

Signed-off-by: YAO Matrix <matrix.yao@intel.com>

* add cross refererence

Signed-off-by: YAO Matrix <matrix.yao@intel.com>

* fix style

Signed-off-by: YAO Matrix <matrix.yao@intel.com>

---------

Signed-off-by: YAO Matrix <matrix.yao@intel.com>
Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
This commit is contained in:
Yao Matrix
2025-04-07 22:02:14 +08:00
committed by GitHub
parent e7ad077012
commit 12bf24d6ae
3 changed files with 47 additions and 33 deletions

View File

@@ -13,14 +13,16 @@ class ExpectationsTest(unittest.TestCase):
("rocm", 8): 4,
("rocm", None): 5,
("cpu", None): 6,
("xpu", 3): 7,
}
)
def check(value, key):
assert expectations.find_expectation(key) == value
# xpu has no matches so should find default expectation
check(1, ("xpu", None))
# npu has no matches so should find default expectation
check(1, ("npu", None))
check(7, ("xpu", 3))
check(2, ("cuda", 8))
check(3, ("cuda", 7))
check(4, ("rocm", 9))