norm.py

import torch
import subprocess
import os

subprocess.call('pip install einops', shell=True)
subprocess.call('pip install flash-attn==1.0.3.post0', shell=True)
print('Installing einops and flash-attn...')
print('Done.')
print('Loading MPT-7B Storywriter 4bit 128G... Please wait...')
def _cast_if_autocast_enabled(tensor):
    if torch.is_autocast_enabled():
        if tensor.device.type == 'cuda':
            dtype = torch.get_autocast_gpu_dtype()
        elif tensor.device.type == 'cpu':
            dtype = torch.get_autocast_cpu_dtype()
        else:
            raise NotImplementedError()
        return tensor.to(dtype=dtype)
    return tensor

class LPLayerNorm(torch.nn.LayerNorm):

    def __init__(self, normalized_shape, eps=1e-05, elementwise_affine=True, device=None, dtype=None):
        super().__init__(normalized_shape=normalized_shape, eps=eps, elementwise_affine=elementwise_affine, device=device, dtype=dtype)

    def forward(self, x):
        module_device = x.device
        downcast_x = _cast_if_autocast_enabled(x)
        downcast_weight = _cast_if_autocast_enabled(self.weight) if self.weight is not None else self.weight
        downcast_bias = _cast_if_autocast_enabled(self.bias) if self.bias is not None else self.bias
        with torch.autocast(enabled=False, device_type=module_device.type):
            return torch.nn.functional.layer_norm(downcast_x, self.normalized_shape, downcast_weight, downcast_bias, self.eps)

def rms_norm(x, weight=None, eps=1e-05):
    output = x / torch.rsqrt(x.pow(2).mean(-1, keepdim=True) + eps)
    if weight is not None:
        return output * weight
    return output

class RMSNorm(torch.nn.Module):

    def __init__(self, normalized_shape, eps=1e-05, weight=True, dtype=None, device=None):
        super().__init__()
        self.eps = eps
        if weight:
            self.weight = torch.nn.Parameter(torch.ones(normalized_shape, dtype=dtype, device=device))
        else:
            self.register_parameter('weight', None)

    def forward(self, x):
        return rms_norm(x.float(), self.weight, self.eps).to(dtype=x.dtype)

class LPRMSNorm(RMSNorm):

    def __init__(self, normalized_shape, eps=1e-05, weight=True, dtype=None, device=None):
        super().__init__(normalized_shape=normalized_shape, eps=eps, weight=weight, dtype=dtype, device=device)

    def forward(self, x):
        downcast_x = _cast_if_autocast_enabled(x)
        downcast_weight = _cast_if_autocast_enabled(self.weight) if self.weight is not None else self.weight
        with torch.autocast(enabled=False, device_type=x.device.type):
            return rms_norm(downcast_x, downcast_weight, self.eps).to(dtype=x.dtype)
NORM_CLASS_REGISTRY = {'layernorm': torch.nn.LayerNorm, 'low_precision_layernorm': LPLayerNorm, 'rmsnorm': RMSNorm, 'low_precision_rmsnorm': LPRMSNorm}