PR #3552 Enable llama.cpp on s390x big endian platform

Enable llama.cpp on s390x big endian platform #3552

ggerganov merged 10 commits into ggml-org:master from chenqiny:master

check whether platform is 390x if yes->do not import immintrin.h

06135624

support s390x big endian

fa62c8c7

support --bigendian option for s390x

1ce890a7

Merge branch 'ggerganov:master' into master

8640f3bb

update format based on editor-config checker result

e4efbdb8

ggerganov approved these changes on 2023-10-10

ggerganov added need feedback

ggerganov commented on 2023-10-11

Update convert-baichuan-hf-to-gguf.py

51e9d391

ggerganov requested a review from

monatis 1 year ago

monatis requested changes on 2023-10-11

cebtenzzre commented on 2023-10-11

1. check in ggml.c if endianess is not match

7fc0250d

chenqiny requested a review from

monatis 1 year ago

always use "GGUF" as beginng of GGUF file

e513abe3

monatis requested changes on 2023-10-17

Compare "GGUF" with file header char by char

eb5b8327

Merge branch 'ggerganov:master' into master

4389bdac

ggerganov requested a review from

monatis 1 year ago

ggerganov approved these changes on 2023-10-20

monatis approved these changes on 2023-10-20

ggerganov merged 8cf19d60 into master 1 year ago

Reviewers

monatis

ggerganov

cebtenzzre

Assignees

No one assigned

Labels

need feedback

Milestone

No milestone

llama.cpp Enable llama.cpp on s390x big endian platform #3552 Merged

Enable llama.cpp on s390x big endian platform #3552

llama.cpp
Enable llama.cpp on s390x big endian platform
#3552

Merged