Function check_params

inference/minimax-text-01.py:34–38

(args, hf_config: AutoConfig)

def check_params(args, hf_config: AutoConfig):
    if args.quant_type == "int8":
        assert args.world_size >= 8, "int8 weight-only quantization requires at least 8 GPUs"

    assert hf_config.num_hidden_layers % args.world_size == 0, f"num_hidden_layers({hf_config.num_hidden_layers}) must be divisible by world_size({args.world_size})"


@torch.no_grad()