add the missing flash attention test marker (#32419)

* add flash attention check * fix * fix * add the missing marker * bug fix * add one more * remove order * add one more
2024-08-06 18:18:58 +08:00
parent 0aa8328293
commit e85d86398a
7 changed files with 9 additions and 2 deletions
--- a/tests/models/qwen2_moe/test_modeling_qwen2_moe.py
+++ b/tests/models/qwen2_moe/test_modeling_qwen2_moe.py
@@ -606,6 +606,7 @@ class Qwen2MoeIntegrationTest(unittest.TestCase):
    @require_bitsandbytes
    @slow
    @require_flash_attn
+    @pytest.mark.flash_attn_test
    def test_model_a2_7b_long_prompt(self):
        EXPECTED_OUTPUT_TOKEN_IDS = [306, 338]
        # An input with 4097 tokens that is above the size of the sliding window