Check that torch has flash attention before taking the flash path (fixes CUDA on Windows)

attention.py

@@ -42,6 +42,8 @@ def _fused(q: torch.Tensor) -> bool:
     """Whether the flash kernels take these queries: a GPU in half precision, ROCm or CUDA from Ampere on."""
     if not q.is_cuda or q.dtype not in (torch.float16, torch.bfloat16):
         return False
+    if not torch.backends.cuda.is_flash_attention_available():
+        return False
     return bool(torch.version.hip) or torch.cuda.get_device_capability(q.device)[0] >= 8