aicloud
/
chatglm-6b
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update quantization

This commit is contained in:
duzx16 2023-03-15 21:18:24 +08:00
parent c3dece3f01
commit 0101afdfa7
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
quantization.py
View File

@ -7,7 +7,11 @@ import base64
import ctypes import ctypes
from typing import List from typing import List
from cpm_kernels.kernels.base import LazyKernelCModule, KernelFunction, round_up
try:
from cpm_kernels.kernels.base import LazyKernelCModule, KernelFunction, round_up
except:
pass
class W8A16Linear(torch.autograd.Function): class W8A16Linear(torch.autograd.Function):