runtime error

Exit code: 1. Reason: y", line 451, in sdpa_mask attention_mask = _vmap_expansion_sdpa(mask_function)(batch_arange, head_arange, cache_position, kv_arange) File "/usr/local/lib/python3.10/site-packages/torch/_functorch/apis.py", line 208, in wrapped return vmap_impl( File "/usr/local/lib/python3.10/site-packages/torch/_functorch/vmap.py", line 282, in vmap_impl return _flat_vmap( File "/usr/local/lib/python3.10/site-packages/torch/_functorch/vmap.py", line 432, in _flat_vmap batched_outputs = func(*batched_inputs, **kwargs) File "/usr/local/lib/python3.10/site-packages/torch/_functorch/apis.py", line 208, in wrapped return vmap_impl( File "/usr/local/lib/python3.10/site-packages/torch/_functorch/vmap.py", line 263, in vmap_impl batch_size, flat_in_dims, flat_args, args_spec = _process_batched_inputs( File "/usr/local/lib/python3.10/site-packages/torch/_functorch/vmap.py", line 131, in _process_batched_inputs if in_dim is not None and (in_dim < -arg.dim() or in_dim >= arg.dim()): File "/usr/local/lib/python3.10/site-packages/torch/_dynamo/_trace_wrapped_higher_order_op.py", line 146, in __torch_function__ return func(*args, **(kwargs or {})) File "/usr/local/lib/python3.10/site-packages/spaces/zero/torch/patching.py", line 206, in __torch_function__ fake.data = empty_fake(original) File "/usr/local/lib/python3.10/site-packages/spaces/zero/torch/patching.py", line 79, in empty_fake fake = empty_like_raw_alloc(tensor, requires_grad=tensor.requires_grad) File "/usr/local/lib/python3.10/site-packages/spaces/zero/torch/utils.py", line 17, in empty_like_raw_alloc empty.requires_grad_(kwargs.get('requires_grad', False)) RuntimeError: You are attempting to call Tensor.requires_grad_() (or perhaps using torch.autograd.functional.* APIs) inside of a function being transformed by a functorch transform. This is unsupported, please attempt to use the functorch transforms (e.g. grad, vjp, jacrev, jacfwd, hessian) or call requires_grad_() outside of a function being transformed instead.

Container logs: