Deprecate --disable-flashinfer and introduce --attention-backend (#1380)

2024-09-10 17:11:16 -07:00
parent 3a6e8b6d78
commit 46094e0c1b
13 changed files with 99 additions and 61 deletions
--- a/test/srt/test_triton_attn_backend.py
+++ b/test/srt/test_triton_attn_backend.py
@@ -20,7 +20,7 @@ class TestTritonAttnBackend(unittest.TestCase):
            cls.model,
            cls.base_url,
            timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
-            other_args=["--disable-flashinfer"],
+            other_args=["--attention-backend", "triton"],
        )

    @classmethod