[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
+1 -1
View File
@@ -6,7 +6,7 @@ from typing import Optional
import torch
import torch.nn.functional as F
from vllm._C import ops
from vllm import _custom_ops as ops
from vllm.model_executor.layers.quantization.aqlm import (
dequantize_weight, generic_dequantize_gemm, get_int_dtype,
optimized_dequantize_gemm)