Skip to content

Enable llama.cpp on s390x big endian platform #3552

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ggerganov merged 10 commits into from
Oct 20, 2023
Merged

Enable llama.cpp on s390x big endian platform #3552

Changes from 1 commit
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
0613562
check whether platform is 390x if yes->do not import immintrin.h
chenqiny Oct 2, 2023
fa62c8c
support s390x big endian
chenqiny Oct 8, 2023
1ce890a
support --bigendian option for s390x
chenqiny Oct 9, 2023
8640f3b
Merge branch 'ggerganov:master' into master
chenqiny Oct 9, 2023
e4efbdb
update format based on editor-config checker result
chenqiny Oct 9, 2023
51e9d39
Update convert-baichuan-hf-to-gguf.py
ggerganov Oct 11, 2023
7fc0250
1. check in ggml.c if endianess is not match
chenqiny Oct 12, 2023
e513abe
always use "GGUF" as beginng of GGUF file
chenqiny Oct 15, 2023
eb5b832
Compare "GGUF" with file header char by char
chenqiny Oct 20, 2023
4389bda
Merge branch 'ggerganov:master' into master
chenqiny Oct 20, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
update format based on editor-config checker result
  • Loading branch information
@chenqiny
chenqiny committed Oct 9, 2023
commit e4efbdb8c181cce356e3d03ef7adea608729b17e
3 changes: 0 additions & 3 deletions gguf-py/gguf/gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -647,8 +647,6 @@ def __init__(self, path: os.PathLike[str] | str, arch: str, use_temp_file = True
self.add_architecture()
self.use_temp_file = use_temp_file
self.tensors = []


print(f"This gguf file is for {self.endianess} only")

def write_header_to_file(self):
Expand Down Expand Up @@ -727,7 +725,6 @@ def add_array(self, key: str, val: Sequence[Any]):
self.add_key(key)
self.add_val(val, GGUFValueType.ARRAY)


def add_val(self, val: Any, vtype: GGUFValueType | None = None, add_vtype: bool = True):
if vtype is None:
vtype = GGUFValueType.get_type(val)
Expand Down