Fix FA2 fallback for Blackwell V1 (#19781)

Signed-off-by: mgoin <mgoin64@gmail.com>

Fix FA2 fallback for Blackwell V1 (#19781)
Signed-off-by: mgoin <mgoin64@gmail.com>
36239f79 · Michael Goin · GitHub · dfada85e · 36239f79
Unverified Commit 36239f79 authored Jun 19, 2025 by Michael Goin Committed by GitHub Jun 19, 2025
Hide whitespace changes
Inline Side-by-side

Showing with 1 addition and 1 deletion

vllm/platforms/cuda.py vllm/platforms/cuda.py +1 -1

No files found.
--- a/vllm/platforms/cuda.py
+++ b/vllm/platforms/cuda.py
@@ -255,7 +255,7 @@ class CudaPlatformBase(Platform):
                        "install FlashInfer for better performance.")
                    pass
            # FlashAttention is the default for SM 8.0+ GPUs
-            elif cls.has_device_capability(80):
+            if cls.has_device_capability(80):
                logger.info_once("Using Flash Attention backend on V1 engine.")
                return ("vllm.v1.attention.backends."
                        "flash_attn.FlashAttentionBackend")