ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-24 08:29:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

iq1_kt: add to constants.py

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-07-17 18:56:07 +03:00
parent a65acba08a
commit 77eaa532c7
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
gguf-py/gguf/constants.py
View File

@@ -1322,6 +1322,7 @@ class GGMLQuantizationType(IntEnum):
IQ4_KT = 155
IQ3_KS = 156
IQ2_KL = 157
IQ1_KT = 158
Q4_0_R8 = 202
Q5_0_R4 = 206
Q8_0_R8 = 208
@@ -1539,6 +1540,7 @@ GGML_QUANT_SIZES: dict[GGMLQuantizationType, tuple[int, int]] = {
GGMLQuantizationType.IQ4_KT : ( 256, 128),
GGMLQuantizationType.IQ3_KS : ( 256, 102),
GGMLQuantizationType.IQ2_KL : ( 256, 86),
GGMLQuantizationType.IQ1_KT : ( 256, 56),
GGMLQuantizationType.Q4_0_R8 : ( 32, 18),
GGMLQuantizationType.Q5_0_R4 : ( 32, 22),
GGMLQuantizationType.Q8_0_R8 : ( 32, 34),