ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-28 18:32:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

WIP + adding iq3_kl quantization mix

Browse Source
This commit is contained in:
Iwan Kawrakow
2024-10-08 13:56:29 +03:00
parent 4c76471979
commit 1dd6c40c15
11 changed files with 110 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
include/llama.h
View File

@@ -178,6 +178,7 @@ extern "C" {
LLAMA_FTYPE_MOSTLY_IQ2_TN = 143, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ1_TN = 144, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ4_XXS = 145, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ3_KL = 146, // except 1d tensors
LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file
};