ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-22 23:49:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

Rename q4_0_r4, q8_0_r4 and iq4_xs_r4 to _r8 (#189)

Browse Source 
* Rename q4_0_r4 to q4_0_r8 to reflect actual row interleaving

* Rename q8_0_r4 to q8_0_r8 to reflect actual row interleaving

* Rename iq4_xs_r4 to iq4_xs_r8 to reflect actual row interleaving

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-02-06 18:45:28 +02:00
committed by GitHub
parent 7c94c3da56
commit 8049ffcbc8
10 changed files with 196 additions and 196 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
ggml/include/ggml.h
View File

@@ -416,9 +416,9 @@ extern "C" {
GGML_TYPE_Q8_K32 = 148,
GGML_TYPE_Q8_KR8 = 149,
GGML_TYPE_Q4_0_R4 = 202,
GGML_TYPE_Q4_0_R8 = 202,
GGML_TYPE_Q5_0_R4 = 206,
GGML_TYPE_Q8_0_R4 = 208,
GGML_TYPE_Q8_0_R8 = 208,
GGML_TYPE_Q2_K_R4 = 210,
GGML_TYPE_Q3_K_R4 = 211,
GGML_TYPE_Q4_K_R4 = 212,
@@ -431,7 +431,7 @@ extern "C" {
GGML_TYPE_IQ4_NL_R4 = 220,
GGML_TYPE_IQ3_S_R4 = 221,
GGML_TYPE_IQ2_S_R4 = 222,
GGML_TYPE_IQ4_XS_R4 = 223,
GGML_TYPE_IQ4_XS_R8 = 223,
GGML_TYPE_IQ1_M_R4 = 229,
GGML_TYPE_BF16_R16 = 230,
GGML_TYPE_Q6_0_R4 = 233,
@@ -501,8 +501,8 @@ extern "C" {
GGML_FTYPE_MOSTLY_IQ2_KS = 138, // except 1d tensors
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_Q4_0_R8 = 202, // except 1d tensors
GGML_FTYPE_MOSTLY_Q8_0_R8 = 207, // except 1d tensors
GGML_FTYPE_MOSTLY_Q5_0_R4 = 208, // except 1d tensors
GGML_FTYPE_MOSTLY_Q2_K_R4 = 210, // except 1d tensors
GGML_FTYPE_MOSTLY_Q3_K_R4 = 211, // except 1d tensors
@@ -516,7 +516,7 @@ extern "C" {
GGML_FTYPE_MOSTLY_IQ4_NL_R4 = 219, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ3_S_R4 = 220, // 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_IQ4_XS_R8 = 222, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ1_M_R4 = 223, // except 1d tensors
GGML_FTYPE_MOSTLY_BF16_R16 = 224, // except 1d tensors
GGML_FTYPE_MOSTLY_Q6_0_R4 = 227, // except 1d tensors