runtime error

Exit code: 1. Reason: rget_text="Hello, this is the first test sentence.", ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ max_len=10, ^^^^^^^^^^^ ) ^ File "/usr/local/lib/python3.13/site-packages/voxcpm/model/voxcpm.py", line 335, in generate return next(self._generate(*args, streaming=False, **kwargs)) File "/usr/local/lib/python3.13/site-packages/torch/utils/_contextlib.py", line 40, in generator_context response = gen.send(None) File "/usr/local/lib/python3.13/site-packages/voxcpm/model/voxcpm.py", line 459, in _generate latent_pred, pred_audio_feat = next(inference_result) ~~~~^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/torch/utils/_contextlib.py", line 40, in generator_context response = gen.send(None) File "/usr/local/lib/python3.13/site-packages/voxcpm/model/voxcpm.py", line 807, in _inference lm_hidden = self.base_lm.forward_step( ~~~~~~~~~~~~~~~~~~~~~~~~~^ curr_embed[:, 0, :], torch.tensor([self.base_lm.kv_cache.step()], device=curr_embed.device) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ).clone() ^ File "/usr/local/lib/python3.13/site-packages/voxcpm/modules/minicpm4/model.py", line 402, in forward_step hidden_states = decoder_layer.forward_step( hidden_states, ...<2 lines>... self.kv_cache.get_layer_cache(i), ) File "/usr/local/lib/python3.13/site-packages/voxcpm/modules/minicpm4/model.py", line 303, in forward_step hidden_states = self.self_attn.forward_step( hidden_states=hidden_states, ...<2 lines>... kv_cache=kv_cache, ) File "/usr/local/lib/python3.13/site-packages/voxcpm/modules/minicpm4/model.py", line 211, in forward_step attn_output = torch.nn.functional.scaled_dot_product_attention( query_states, ...<3 lines>... enable_gqa=True, ) IndexError: Dimension out of range (expected to be in range of [-1, 0], but got -2)

Container logs: