[V0 Deprecation] Remove V0 FlashInfer attention backend (#22776)

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-08-18 19:54:16 -07:00
parent 6603288736
commit 14006840ea
8 changed files with 9 additions and 1133 deletions
--- a/tests/compile/test_basic_correctness.py
+++ b/tests/compile/test_basic_correctness.py
@@ -34,7 +34,7 @@ class TestSetting:
            model_args=["--max-model-len", "2048"],
            pp_size=2,
            tp_size=2,
-            attn_backend="FLASHINFER",
+            attn_backend="FLASH_ATTN",
            method="generate",
            fullgraph=True,
        ),