weight:
 bit: 8
 symmetric: True
 granularity: per_channel
 group_size: -1
 calib_algo: mse
 act:
 bit: 8
 symmetric: True
 granularity: per_token
 calib_algo: minmax
 special:
 actorder: True
 static_groups: False
 percdamp: 0.01
 blocksize: 128
 chunk_num: 4
 true_sequential: True
 online_rotate: False
 fp32_had: True

 def weight_transform(self, W, Hinv, Losses, tmp):
 # NOTE:
 curr_blocksize = self.blocksize
 if curr_blocksize <= 0:
 logger.info('Blocksize < 0 , using perchannel GPTQ')
 curr_blocksize = W.shape[1]
 print(f'=== W.shape:{W.shape}')
 
 for i1 in range(0, self.n_nonout, curr_blocksize):
 # for i1 in range(0, self.n_nonout, self.blocksize):
 i2 = min(i1 + curr_blocksize, self.n_nonout)
 count = i2 - i1
 W1, Hinv1 = W[:, i1:i2].clone(), Hinv[i1:i2, i1:i2]
 tmp1, Err1, Losses1 = (
 torch.zeros_like(W1),
 torch.zeros_like(W1),
 torch.zeros_like(W1),
 )
 for i in range(count):
 w, d = W1[:, i], Hinv1[i, i]
 if self.wquantizer.granularity == 'per_group':
 idx = i1 + i
 if not self.static_groups:
 if (i1 + i) % self.wquantizer.group_size == 0:
 column_tensors = W[
 :,
 (i1 + i): min(
 (i1 + i + self.wquantizer.group_size),
 (self.columns - self.n_out),
 ),
 ]
 self.search_column_qparams(column_tensors, idx)
 else:
 if self.actorder:
 idx = self.perm[idx]
 self.qparams = self.groups[idx // self.wquantizer.group_size]
 q = self.wquantizer.quant_dequant(
 w.unsqueeze(1),
 self.qparams['scale'],
 self.qparams['zero'],
 self.qparams['qmax'],
 self.qparams['qmin'],
 ).squeeze(1)
 tmp1[:, i] = w
 Losses1[:, i] = ((w - q) ** 2) / (2 * d**2)
 err1 = (w - q) / d
 W1[:, i:] -= err1.unsqueeze(1).matmul(Hinv1[i, i:].unsqueeze(0))
 Err1[:, i] = err1
 tmp[:, i1:i2], Losses[:, i1:i2] = tmp1, Losses1
 W[:, i2:] -= Err1.matmul(Hinv[i1:i2, i2:])