File "/home/supermicro/miniconda3/envs/nvidia/lib/python3.10/site-packages/transformers/generation/utils.py", line 1455, in generate
    return self.assisted_decoding(
  File "/home/supermicro/miniconda3/envs/nvidia/lib/python3.10/site-packages/transformers/generation/utils.py", line 4397, in assisted_decoding
    n_matches = ((~(candidate_new_tokens == selected_tokens[:, :-1])).cumsum(dim=-1) < 1).sum()
RuntimeError: The size of tensor a (10) must match the size of tensor b (0) at non-singleton dimension 1