diff options
author | Georgi Gerganov <ggerganov@gmail.com> | 2023-08-27 14:19:54 +0300 |
---|---|---|
committer | GitHub <noreply@github.com> | 2023-08-27 14:19:54 +0300 |
commit | d0cee0d36d5be95a0d9088b674dbb27354107221 (patch) | |
tree | bb5db56b4d1a9ea71eb1651485a38034b6acc3f2 /llama.cpp | |
parent | edd4c1481708fcd788b0e423268304fd26e2b125 (diff) |
gguf : add 64-bit support (GGUF v2) (#2821)
* gguf : bump version to 2
* gguf : add support for 64-bit (no backwards comp yet)
* gguf : v1 backwards comp
* gguf.py : bump GGUF version
* gguf.py : uint64_t on all lengths, sizes and counts, enums still uint32_t
* gguf.py : string lengths uint32_t
* gguf : update all counts to 64-bit
* gguf.py : string len uint64_t and n_dims uint32_t
* gguf : fix typo
* llama.cpp : print gguf version
---------
Co-authored-by: klosax <131523366+klosax@users.noreply.github.com>
Diffstat (limited to 'llama.cpp')
-rw-r--r-- | llama.cpp | 4 |
1 files changed, 3 insertions, 1 deletions
@@ -1144,11 +1144,13 @@ static bool llama_kv_cache_init( enum llama_fver { GGUF_FILE_VERSION_V1 = 1, + GGUF_FILE_VERSION_V2 = 2, }; static const char * llama_file_version_name(llama_fver version) { switch (version) { - case GGUF_FILE_VERSION_V1: return "GGUF V1 (latest)"; + case GGUF_FILE_VERSION_V1: return "GGUF V1 (support until nov 2023)"; + case GGUF_FILE_VERSION_V2: return "GGUF V2 (latest)"; } return "unknown"; |