ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-25 17:09:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

Adding q5_0_r4

Browse Source 
We get PP-512(LLaMA-3.1-8B) = 256.7 t/s on a Ryzen-7950X.
We even get TG-128 improvement to 11.7 t/s from 11.1 t/s.
This commit is contained in:
Iwan Kawrakow
2024-12-03 11:29:57 +02:00
parent ccec00939a
commit fad847d753
10 changed files with 323 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/include/ggml.h
View File

@@ -408,8 +408,10 @@ extern "C" {
GGML_TYPE_IQ4_KSS = 146,
GGML_TYPE_Q4_0_R4 = 202,
GGML_TYPE_Q5_0_R4 = 206,
GGML_TYPE_Q8_0_R4 = 208,
GGML_TYPE_IQ4_NL_X4 = 220,
GGML_TYPE_Q6_0_R4 = 233,
GGML_TYPE_COUNT,
};
@@ -471,7 +473,9 @@ extern "C" {
//
GGML_FTYPE_MOSTLY_Q4_0_R4 = 202, // except 1d tensors
GGML_FTYPE_MOSTLY_Q8_0_R4 = 207, // except 1d tensors
GGML_FTYPE_MOSTLY_Q5_0_R4 = 208, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ4_NL_X4 = 219, // except 1d tensors
GGML_FTYPE_MOSTLY_Q6_0_R4 = 227, // except 1d tensors
};
// available tensor operations: