vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

gguf : support big endian platform (#3552)

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

* support s390x big endian

* support --bigendian option for s390x
1. verified with baichuan7b-chat with float 16 on s390x
2. verified with baichuan7b-chat
3. verified with chinese-alpaca-2-13b-f16

* update format based on editor-config checker result

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

* 1. check in ggml.c if endianess is not match
2. update GGUF version
3. change get_pack_prefix to property
4. update information log

* always use "GGUF" as beginng of GGUF file

* Compare "GGUF" with file header char by char
1.  Set GGUF_MAGIC to "GGUF" string instead of int value
2. Compare "GGUF" char by char to ensure its byte order
3. Move bytes swap code from convert.py to gguf.py write_tensor_data

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Qin Yue Chen 2023-10-20 06:19:40 -05:00 • committed by GitHub
parent a0edf73bda
commit 8cf19d60dc
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
9 changed files with 84 additions and 49 deletions
Download patch file Download diff file Expand all files Collapse all files

2
tests/test-double-float.cpp
View file

@ -4,7 +4,9 @@
#undef NDEBUG
#include <cassert>
#if !defined(__riscv) && !defined(__s390__)
#include <immintrin.h>
#endif
#include <cmath>
#include <cstdint>
#include <cstring>