silver
/

chatglm-6b-slim

Inference Endpoints

Model card Files Files and versions Community

zxdu20 commited on Mar 15, 2023

Commit

0d8b08d

•

1 Parent(s): 0101afd

Revert "Update quantization"

This reverts commit 0101afdfa7f279e082623ee57d7ad6f84e1e82dc.

Files changed (1) hide show

quantization.py +1 -5

quantization.py CHANGED Viewed

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

 import ctypes
 from typing import List
+from cpm_kernels.kernels.base import LazyKernelCModule, KernelFunction, round_up
 class W8A16Linear(torch.autograd.Function):