CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-14 11:07:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

convert : fix reflinks for stacked MoE tensors

Browse Source
This commit is contained in:
Francis Couture-Harpin
2025-09-02 15:22:01 -04:00
parent 562aa42c12
commit d921057027
4 changed files with 31 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
gguf-py/gguf/lazy.py
View File

@@ -21,7 +21,7 @@ class LazyMeta(ABCMeta):
return type(self)._wrap_fn(
(lambda s, *args, **kwargs: getattr(s, name)(*args, **kwargs)),
use_self=self,
data_noop=name in ("view", "reshape", "squeeze", "unsqueeze"),
data_noop=name in ("view", "reshape", "squeeze", "unsqueeze", "contiguous"),
)
elif isinstance(meta_attr, self._tensor_type):
# e.g. self.T with torch.Tensor should still be wrapped