ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-04 19:10:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

iq5_k: Basics

Browse Source 
Quantize/dequantize, CUDA dequantize
This commit is contained in:
Iwan Kawrakow
2024-07-29 12:38:46 +03:00
parent 1c2d026da6
commit f0836bdbbe
14 changed files with 650 additions and 178 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
include/llama.h
View File

@@ -170,8 +170,9 @@ extern "C" {
LLAMA_FTYPE_MOSTLY_Q4_0_8_8 = 35, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ1_BN = 36, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ2_BN = 37, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ4_K = 38, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ2_K = 39, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ2_K = 38, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ4_K = 39, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ5_K = 40, // except 1d tensors
LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file
};