[Bugfix][SM120][MLA] Disable dense prefill for FlashInfer sparse MLA (#51395)
Signed-off-by: tommy-asai-sonarsource <yosuke.asai@sonarsource.com> Co-authored-by: Roger Wang <hey@rogerw.io>
This commit is contained in:
@@ -34,6 +34,13 @@ def test_sm120_backend_uses_dedicated_backend_name() -> None:
|
||||
)
|
||||
|
||||
|
||||
def test_sm120_backend_uses_sparse_mqa_for_prefill() -> None:
|
||||
impl_cls = FlashInferMLASparseSM120Backend.get_impl_cls()
|
||||
|
||||
assert impl_cls.is_sparse
|
||||
assert not impl_cls.supports_dense_mha_prefill
|
||||
|
||||
|
||||
def test_v32_glm_sm120_backend_accepts_glm_block_size(
|
||||
monkeypatch,
|
||||
) -> None:
|
||||
|
||||
@@ -33,6 +33,7 @@ class FlashInferMLASparseSM120Impl(MLAAttentionImpl[FlashInferMLASparseMetadata]
|
||||
"""SM120 FlashInfer sparse-MLA implementation."""
|
||||
|
||||
is_sparse = True
|
||||
supports_dense_mha_prefill = False
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
|
||||
Reference in New Issue
Block a user