CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-10 10:27:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

convert : write tensors in parallel

Browse Source
This commit is contained in:
Francis Couture-Harpin
2025-04-08 16:31:45 -04:00
parent b32efad2bc
commit 06e1d3119a
3 changed files with 95 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
gguf-py/gguf/lazy.py
View File

@@ -220,4 +220,9 @@ class LazyNumpyTensor(LazyBase):
eager = LazyNumpyTensor.to_eager(self)
return eager.tofile(*args, **kwargs)
@property
def data(self):
eager = LazyNumpyTensor.to_eager(self)
return eager.data
# TODO: __array_function__