llama.cpp
gguf : add 64-bit support (GGUF v2)
#2821
Merged

gguf : add 64-bit support (GGUF v2) #2821

ggerganov merged 10 commits into master from gguf-64bit
ggerganov
ggerganov gguf : bump version to 2
5f1fffd2
klosax
ggerganov gguf : add support for 64-bit (no backwards comp yet)
4f0547e4
ggerganov
ggerganov gguf : v1 backwards comp
3656b3ce
ggerganov ggerganov marked this pull request as ready for review 2 years ago
ggerganov ggerganov changed the title gguf : add 64-bit support gguf : add 64-bit support (GGUF v2) 2 years ago
ggerganov gguf.py : bump GGUF version
ba335ff5
klosax
klosax gguf.py : uint64_t on all lengths, sizes and counts, enums still uint…
be726c57
klosax gguf.py : string lengths uint32_t
bc3eaf26
ggerganov gguf : update all counts to 64-bit
6d369a15
klosax gguf.py : string len uint64_t and n_dims uint32_t
09b6da74
cebtenzzre
cebtenzzre commented on 2023-08-26
ggerganov gguf : fix typo
b61b1700
KerfuffleV2
ghost
klosax llama.cpp : print gguf version
33a5517d
klosax
klosax approved these changes on 2023-08-26
klosax
philpax
ghost
klosax
KerfuffleV2
ghost
ggerganov
ggerganov ggerganov merged d0cee0d3 into master 2 years ago
pudepiedj
Green-Sky
pudepiedj
KerfuffleV2

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone