ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-24 16:39:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

IQ2_S_R4 (#156)

Browse Source 
* iq2_s_r4: Zen4

* Minor

* iq2_s_r4: NEON

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2024-12-21 11:26:35 +01:00
committed by GitHub
parent 6892554e43
commit 7598ec79a2
10 changed files with 355 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/include/ggml.h
View File

@@ -422,6 +422,7 @@ extern "C" {
GGML_TYPE_IQ2_XS_R4 = 217,
GGML_TYPE_IQ3_XXS_R4= 218,
GGML_TYPE_IQ4_NL_R4 = 220,
GGML_TYPE_IQ2_S_R4 = 222,
GGML_TYPE_IQ4_XS_R4 = 223,
GGML_TYPE_BF16_R16 = 230,
GGML_TYPE_Q6_0_R4 = 233,
@@ -503,6 +504,7 @@ extern "C" {
GGML_FTYPE_MOSTLY_IQ2_XS_R4 = 216, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ3_XXS_R4= 217, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ4_NL_R4 = 219, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ2_S_R4 = 221, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ4_XS_R4 = 222, // except 1d tensors
GGML_FTYPE_MOSTLY_BF16_R16 = 224, // except 1d tensors
GGML_FTYPE_MOSTLY_Q6_0_R4 = 227, // except 1d tensors