vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-10 23:34:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix rope; update moegate

Browse source
This commit is contained in:
Azure 2025-02-01 18:05:45 +00:00
parent f873558a89
commit f748cd29f0
5 changed files with 54 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ktransformers/operators/linear.py
View file

@ -222,7 +222,7 @@ class KLinearMarlin(KLinearBase):
x = x.to(self.device)
orig_shape = list(x.shape)
orig_dtype = x.dtype
x = x.reshape(-1, x.shape[-1])
x = x.reshape(-1, orig_shape[-1])
marlin_s = self.marlin_s.to(x.dtype)
x = KTransformersOps.gptq_marlin_gemm(
x,