[Bugfix] Enable FlashAttention MLA prefill for Mistral Small 4 head dims (#48855)

Signed-off-by: juliendenize <julien.denize@mistral.ai>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
This commit is contained in:
Julien Denize
2026-07-17 18:07:00 +08:00
committed by GitHub
co-authored by Nicolò Lucchesi
parent d5b1ec2684
commit ce4bdcbda4
3 changed files with 10 additions and 5 deletions
@@ -125,8 +125,8 @@ class TestGetMLAPrefillBackend:
@pytest.mark.parametrize(
("qk_nope_head_dim", "v_head_dim"),
[(128, 128), (192, 256)],
ids=["deepseek", "glm"],
[(128, 128), (192, 256), (64, 128)],
ids=["deepseek", "glm", "mistral_s4"],
)
def test_auto_selection_on_hopper(self, qk_nope_head_dim: int, v_head_dim: int):
try: