[v1] Add PrefixLM support to FlexAttention backend (#27938)

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-12-07 23:51:36 +08:00
parent 541a2ef892
commit b952f4d3c3
16 changed files with 173 additions and 25 deletions
--- a/tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/dummy_platform.py
+++ b/tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/dummy_platform.py
@@ -30,5 +30,6 @@ class DummyPlatform(Platform):
        use_mla,
        has_sink,
        use_sparse,
+        use_mm_prefix,
    ):
        return "vllm_add_dummy_platform.dummy_attention_backend.DummyAttentionBackend"  # noqa E501