llama.cpp
gguf : add 64-bit support (GGUF v2)
#2821
Merged
Overview
Commits
10
Changes
View On GitHub
Commits
  • gguf : bump version to 2
    ggerganov committed 2 years ago
  • gguf : add support for 64-bit (no backwards comp yet)
    ggerganov committed 2 years ago
  • gguf : v1 backwards comp
    ggerganov committed 2 years ago
  • gguf.py : bump GGUF version
    ggerganov committed 2 years ago
  • gguf.py : uint64_t on all lengths, sizes and counts, enums still uint32_t
    klosax committed 2 years ago
  • gguf.py : string lengths uint32_t
    klosax committed 2 years ago
  • gguf : update all counts to 64-bit
    ggerganov committed 2 years ago
  • gguf.py : string len uint64_t and n_dims uint32_t
    klosax committed 2 years ago
  • gguf : fix typo
    ggerganov committed 2 years ago
  • llama.cpp : print gguf version
    klosax committed 2 years ago
FAQ Terms Privacy Refunds Impressum
Loading