Fix failing tests for mimo_v2_flash (#47284)
* fix(mimo_v2_flash): auto-fix failing tests
Fixed 11 test(s):
- tests/models/mimo_v2_flash/test_modeling_mimo_v2_flash.py::MiMoV2FlashModelTest::test_eager_matches_fa2_generate
- tests/models/mimo_v2_flash/test_modeling_mimo_v2_flash.py::MiMoV2FlashModelTest::test_flash_attention_2_continue_generate_with_position_ids
- tests/models/mimo_v2_flash/test_modeling_mimo_v2_flash.py::MiMoV2FlashModelTest::test_flash_attention_2_padding_matches_padding_free_with_position_ids
- tests/models/mimo_v2_flash/test_modeling_mimo_v2_flash.py::MiMoV2FlashModelTest::test_flash_attention_2_padding_matches_padding_free_with_position_ids_and_fa_kwargs
- tests/models/mimo_v2_flash/test_modeling_mimo_v2_flash.py::MiMoV2FlashModelTest::test_flash_attn_2_equivalence
- tests/models/mimo_v2_flash/test_modeling_mimo_v2_flash.py::MiMoV2FlashModelTest::test_flash_attn_2_fp32_ln
- tests/models/mimo_v2_flash/test_modeling_mimo_v2_flash.py::MiMoV2FlashModelTest::test_flash_attn_2_from_config
- tests/models/mimo_v2_flash/test_modeling_mimo_v2_flash.py::MiMoV2FlashModelTest::test_generate_with_quant_cache
- tests/models/mimo_v2_flash/test_modeling_mimo_v2_flash.py::MiMoV2FlashModelTest::test_kernels_can_load_without_crashing
- tests/models/mimo_v2_flash/test_modeling_mimo_v2_flash.py::MiMoV2FlashIntegrationTest::test_small_model_generation
- ... and 1 more
* update
Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>
* update
Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>
* update
Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>
* skip test_generate_with_quant_cache
Signed-off-by: kaixuanliu <kaixuan.liu@intel.com>
* use `no_inherit_decorator`
Signed-off-by: kaixuanliu <kaixuan.liu@intel.com>
* current Glm4MoeConfig no longer defines num_mtp_layers
Signed-off-by: kaixuanliu <kaixuan.liu@intel.com>
* update
Signed-off-by: kaixuanliu <kaixuan.liu@intel.com>
---------
Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>
Signed-off-by: kaixuanliu <kaixuan.liu@intel.com>
