| engine=DeepSpeed | |
| option.entryPoint=inference.py | |
| option.tensor_parallel_degree=1 | |
| option.max_tokens=4096 | |
| option.task=text-generation | |
| option.dtype=bf16 | |
| option.model_type=base | |
| option.model_loading_timeout=3600 |
| engine=DeepSpeed | |
| option.entryPoint=inference.py | |
| option.tensor_parallel_degree=1 | |
| option.max_tokens=4096 | |
| option.task=text-generation | |
| option.dtype=bf16 | |
| option.model_type=base | |
| option.model_loading_timeout=3600 |