Enable llama.cpp on s390x big endian platform#3552

Merged

ggerganov merged 10 commits intoggml-org:masterfrom chenqiny:master

Oct 20, 2023

+84-49

Commits on Oct 2, 2023

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

Commits on Oct 8, 2023

support s390x big endian
chenqiny
committed

Commits on Oct 9, 2023

Commits on Oct 11, 2023

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

Commits on Oct 12, 2023

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

Commits on Oct 15, 2023

always use "GGUF" as beginng of GGUF file
chenqiny
committed

Commits on Oct 20, 2023