CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-13 10:57:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml-quants : 1.625 bpw ternary packing for BitNet 1.58b

Browse Source
This commit is contained in:
Francis Couture-Harpin
2024-06-19 12:21:08 -04:00
parent ac146628e4
commit bd807499f7
11 changed files with 594 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/include/ggml.h
View File

@@ -383,6 +383,8 @@ extern "C" {
GGML_TYPE_F64 = 28,
GGML_TYPE_IQ1_M = 29,
GGML_TYPE_BF16 = 30,
GGML_TYPE_Q2_2 = 31,
GGML_TYPE_Q1_3 = 32,
GGML_TYPE_COUNT,
};