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

ggml : add GGML_QNT_VERSION to track quantization format changes

Browse source 
https://github.com/ggerganov/ggml/issues/150#issuecomment-1546625668
This commit is contained in:
Georgi Gerganov 2023-05-14 10:20:19 +03:00
parent 08737ef720
commit 601a033475
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
1 changed files with 3 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
ggml.h
View file

@ -190,6 +190,9 @@
#define GGML_FILE_MAGIC 0x67676d6c // "ggml"
#define GGML_FILE_VERSION 1
#define GGML_QNT_VERSION 1 // bump this on quantization format changes
#define GGML_QNT_VERSION_FACTOR 1000 // do not change this
#define GGML_MAX_DIMS 4
#define GGML_MAX_NODES 4096
#define GGML_MAX_PARAMS 256