ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-25 23:54:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

iq4_knn: Basics + CUDA

Browse Source
This commit is contained in:
Iwan Kawrakow
2024-10-16 18:37:47 +03:00
parent 03cabe1540
commit ebb5eb0fc8
15 changed files with 449 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
include/llama.h
View File

@@ -181,6 +181,7 @@ extern "C" {
LLAMA_FTYPE_MOSTLY_IQ3_KL = 146, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ2_KS = 147, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ4_KSS = 148, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ4_KNN = 149, // except 1d tensors
LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file
};