ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-30 03:11:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

q8_k_r16: basics

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-08-20 08:31:35 +03:00
parent 2572d16399
commit 270b45a481
6 changed files with 122 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/include/ggml.h
View File

@@ -475,6 +475,7 @@ extern "C" {
GGML_TYPE_IQ5_K_R4 = 340,
GGML_TYPE_IQ4_KS_R4 = 344,
GGML_TYPE_IQ5_KS_R4 = 352,
GGML_TYPE_Q8_K_R16 = 397,
GGML_TYPE_Q8_KV_R8 = 398,
GGML_TYPE_Q8_K_R8 = 399,
GGML_TYPE_COUNT,
@@ -571,6 +572,7 @@ extern "C" {
GGML_FTYPE_MOSTLY_IQ5_K_R4 = 333, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ4_KS_R4 = 337, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ5_KS_R4 = 341, // except 1d tensors
GGML_FTYPE_MOSTLY_Q8_K_R16 = 397, // except 1d tensors
GGML_FTYPE_MOSTLY_Q8_KV_R8 = 398, // except 1d tensors
GGML_FTYPE_MOSTLY_Q8_K_R8 = 399, // except 1d tensors
};