ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-29 10:51:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

iq6_k: WIP (quantize/dequantize)

Browse Source
This commit is contained in:
Iwan Kawrakow
2024-08-07 16:49:43 +03:00
parent 54ce23bb61
commit 85f448e2b1
5 changed files with 150 additions and 119 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
include/llama.h
View File

@@ -174,7 +174,8 @@ extern "C" {
LLAMA_FTYPE_MOSTLY_IQ3_K = 39, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ4_K = 40, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ5_K = 41, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ2_TN = 42, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ6_K = 42, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ2_TN = 43, // except 1d tensors
LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file
};