runtime error

Exit code: 1. Reason: [rank0]: self.start_layer, self.end_layer, self.layers = make_layers( [rank0]: File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/models/utils.py", line 282, in make_layers [rank0]: [PPMissingLayer() for _ in range(start_layer)] + [ [rank0]: File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/models/utils.py", line 283, in <listcomp> [rank0]: maybe_offload_to_cpu(layer_fn(prefix=f"{prefix}.{idx}")) [rank0]: File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/models/llama.py", line 294, in <lambda> [rank0]: lambda prefix: LlamaDecoderLayer(config=config, [rank0]: File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/models/llama.py", line 209, in __init__ [rank0]: self.self_attn = LlamaAttention( [rank0]: File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/models/llama.py", line 134, in __init__ [rank0]: self.qkv_proj = QKVParallelLinear( [rank0]: File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/layers/linear.py", line 683, in __init__ [rank0]: super().__init__(input_size=input_size, [rank0]: File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/layers/linear.py", line 284, in __init__ [rank0]: super().__init__(input_size, output_size, skip_bias_add, params_dtype, [rank0]: File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/layers/linear.py", line 172, in __init__ [rank0]: self.quant_method = quant_config.get_quant_method(self, [rank0]: File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/layers/quantization/bitsandbytes.py", line 107, in get_quant_method [rank0]: return BitsAndBytesLinearMethod(self) [rank0]: File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/layers/quantization/bitsandbytes.py", line 128, in __init__ [rank0]: raise ImportError("Please install bitsandbytes>=0.44.0 via " [rank0]: ImportError: Please install bitsandbytes>=0.44.0 via `pip install bitsandbytes>=0.44.0` to use bitsandbytes quantizer.

Container logs: