[CPU] Refactor CPU attention backend (#27954)

Signed-off-by: jiang1.li <jiang1.li@intel.com>
2025-11-12 09:43:06 +08:00
parent e1710393c4
commit 7f829be7d3
34 changed files with 4354 additions and 1902 deletions
--- a/tests/models/language/pooling/test_embedding.py
+++ b/tests/models/language/pooling/test_embedding.py
@@ -23,8 +23,7 @@ from ...utils import check_embeddings_close
        ),
        pytest.param(
            "intfloat/e5-mistral-7b-instruct",
-            # CPU v1 doesn't support sliding window
-            marks=[pytest.mark.core_model],
+            marks=[pytest.mark.core_model, pytest.mark.cpu_model],
        ),
        pytest.param(
            "ssmits/Qwen2-7B-Instruct-embed-base", marks=[pytest.mark.cpu_model]