fixup! Disable TMA by default (#607)

Author: zhiyuan1i

fla/utils.py

@@ -399,7 +399,7 @@ def map_triton_backend_to_torch_device() -> str:
 is_tf32_supported = (is_nvidia and torch.cuda.get_device_capability(0)[0] >= 8)
 is_gather_supported = hasattr(triton.language, 'gather')
 is_tma_supported = (is_nvidia and torch.cuda.get_device_capability(0)[0] >= 9) \
-    and os.environ.get('FLA_USE_TMA', '0') != '1' and \
+    and os.environ.get('FLA_USE_TMA', '0') == '1' and \
     (hasattr(triton.language, '_experimental_make_tensor_descriptor') or hasattr(triton.language, 'make_tensor_descriptor'))
 
 if is_nvidia and not is_tf32_supported: