Refactor attention backend (#1381)

2024-09-11 11:44:26 -07:00
parent c03cece42f
commit fec185ce0c
16 changed files with 568 additions and 564 deletions
--- a/test/srt/test_create_kvindices.py
+++ b/test/srt/test_create_kvindices.py
@@ -55,8 +55,8 @@ class TestCreateKvIndices(unittest.TestCase):
            paged_kernel_lens,
            kv_indptr,
            None,
-            req_to_token.size(1),
            kv_indices_triton,
+            req_to_token.size(1),
        )

        # Check