[Core]Refactor gptq_marlin ops (#4466)

This commit is contained in:
Kunshang Ji
2024-04-30 08:14:47 -04:00
committed by GitHub
parent fa32207842
commit 26f2fb5113
2 changed files with 17 additions and 1 deletions
@@ -6,7 +6,7 @@ import numpy
import torch
from torch.nn.parameter import Parameter
from vllm._C import ops
from vllm import _custom_ops as ops
from vllm.model_executor.layers.linear import (LinearBase, LinearMethodBase,
set_weight_attrs)
from vllm.model_executor.layers.quantization.base_config import (