[Attention] Use sparse prefill kernel for fp8 kv-cache in DeepSeek-v3.2 (#27532)

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2025-12-12 08:57:47 -05:00
parent 91401c7a26
commit 3e41992fec
30 changed files with 1372 additions and 256 deletions
--- a/tests/kernels/moe/test_moe.py
+++ b/tests/kernels/moe/test_moe.py
@@ -231,6 +231,7 @@ def test_fused_moe(
    padding: bool,
    chunk_size: int,
    monkeypatch,
+    workspace_init,
 ):
    current_platform.seed_everything(7)