Skip to content
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

Jump to bottom

Enable llama.cpp on s390x big endian platform #3552

Merged
merged 10 commits into from
Oct 20, 2023
Merged

Enable llama.cpp on s390x big endian platform #3552

merged 10 commits into from
Oct 20, 2023

Commits on Oct 2, 2023

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

    @chenqiny
    chenqiny committed Oct 2, 2023
    Configuration menu
    Copy the full SHA
    0613562 View commit details
    Browse the repository at this point in the history

Commits on Oct 8, 2023

  1. support s390x big endian

    @chenqiny
    chenqiny committed Oct 8, 2023
    Configuration menu
    Copy the full SHA
    fa62c8c View commit details
    Browse the repository at this point in the history

Commits on Oct 9, 2023

  1. 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
    @chenqiny
    chenqiny committed Oct 9, 2023
    Configuration menu
    Copy the full SHA
    1ce890a View commit details
    Browse the repository at this point in the history

  2. Merge branch 'ggerganov:master' into master

    @chenqiny
    chenqiny authored Oct 9, 2023
    Configuration menu
    Copy the full SHA
    8640f3b View commit details
    Browse the repository at this point in the history

  3. update format based on editor-config checker result

    @chenqiny
    chenqiny committed Oct 9, 2023
    Configuration menu
    Copy the full SHA
    e4efbdb View commit details
    Browse the repository at this point in the history

Commits on Oct 11, 2023

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

    @ggerganov
    ggerganov authored Oct 11, 2023
    Configuration menu
    Copy the full SHA
    51e9d39 View commit details
    Browse the repository at this point in the history

Commits on Oct 12, 2023

  1. 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
    @chenqiny
    chenqiny committed Oct 12, 2023
    Configuration menu
    Copy the full SHA
    7fc0250 View commit details
    Browse the repository at this point in the history

Commits on Oct 15, 2023

  1. always use "GGUF" as beginng of GGUF file

    @chenqiny
    chenqiny committed Oct 15, 2023
    Configuration menu
    Copy the full SHA
    e513abe View commit details
    Browse the repository at this point in the history

Commits on Oct 20, 2023

  1. 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
    @chenqiny
    chenqiny committed Oct 20, 2023
    Configuration menu
    Copy the full SHA
    eb5b832 View commit details
    Browse the repository at this point in the history

  2. Merge branch 'ggerganov:master' into master

    @chenqiny
    chenqiny authored Oct 20, 2023
    Configuration menu
    Copy the full SHA
    4389bda View commit details
    Browse the repository at this point in the history