[Bugfix] Fix unsupported FA version check for Turing GPU (#12828)

2025-02-07 01:18:22 +08:00
parent afe74f7a96
commit 8108ac841d
1 changed files with 1 additions and 1 deletions
--- a/vllm/attention/backends/utils.py
+++ b/vllm/attention/backends/utils.py
@@ -612,5 +612,5 @@ try:
        return fa_version

    VLLM_FLASH_ATTN_VERSION = flash_attn_version()
-except ImportError:
+except (ImportError, AssertionError):
    VLLM_FLASH_ATTN_VERSION = None