[Core]refactor aqlm quant ops (#4351)

This commit is contained in:
Kunshang Ji
2024-04-25 15:03:56 -04:00
committed by GitHub
parent bd7a8eef25
commit f4bc4de1b1
3 changed files with 16 additions and 2 deletions
@@ -8,7 +8,7 @@ import torch
import torch.nn.functional as F
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 (LinearMethodBase,
set_weight_attrs)
from vllm.model_executor.layers.quantization.base_config import (