ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-28 18:32:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

Adding q8_0_r4

Browse Source 
We get PP-512(LLaMA-3.1-8B) = 268 t/s on a Ryzen-7950X compared
to 175.6 t/s for Q8_0.
This commit is contained in:
Iwan Kawrakow
2024-12-02 19:22:04 +02:00
parent 239a344f99
commit e1b922d3f3
9 changed files with 237 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/include/ggml.h
View File

@@ -408,6 +408,7 @@ extern "C" {
GGML_TYPE_IQ4_KSS = 146,
GGML_TYPE_Q4_0_R4 = 202,
GGML_TYPE_Q8_0_R4 = 208,
GGML_TYPE_IQ4_NL_X4 = 220,
GGML_TYPE_COUNT,
};
@@ -469,6 +470,7 @@ extern "C" {
GGML_FTYPE_MOSTLY_IQ4_KSS = 139, // except 1d tensors
//
GGML_FTYPE_MOSTLY_Q4_0_R4 = 202, // except 1d tensors
GGML_FTYPE_MOSTLY_Q8_0_R4 = 207, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ4_NL_X4 = 219, // except 1d tensors
};