vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

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

Browse source 
* 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>
This commit is contained in:
Georgi Gerganov 2023-08-27 14:19:54 +03:00 • committed by GitHub
parent edd4c14817
commit d0cee0d36d
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 164 additions and 27 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama.cpp
View file

@ -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";