8000 Releases · chenqiny/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

Releases: chenqiny/llama.cpp

b1562

23 Nov 07:13
@github-actions github-actions
b1562
3afd4c7
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b1562 Latest
Latest 
Merge branch 'ggerganov:master' into master
Assets 12
Loading

b1414

20 Oct 11:36
@github-actions github-actions
b1414
4389bda
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b1414 
Merge branch 'ggerganov:master' into master
Loading

b1363

20 Oct 11:14
@github-actions github-actions
b1363
eb5b832
Compare
Choose a tag to compare
b1363 
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
Loading

b1362

15 Oct 16:29
@github-actions github-actions
b1362
e513abe
Compare
Choose a tag to compare
b1362 
always use "GGUF" as beginng of GGUF file
Loading

b1361

12 Oct 16:57
@github-actions github-actions
b1361
7fc0250
Compare
Choose a tag to compare
b1361 
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
Loading

b1358

09 Oct 03:56
@github-actions github-actions
b1358
8640f3b
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b1358 
Merge branch 'ggerganov:master' into master
Loading

first s390x compatible version

09 Oct 03:09
@chenqiny chenqiny
s390init
1ce890a
Compare
Choose a tag to compare
first s390x compatible version Pre-release
Pre-release 
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
Loading
0