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

iq1_m_r4: basics (quantize/dequantize)

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-02-05 16:59:55 +02:00
parent a6f9f2ec9a
commit 212e8d192e
7 changed files with 342 additions and 226 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/include/ggml.h
View File

@@ -432,6 +432,7 @@ extern "C" {
GGML_TYPE_IQ3_S_R4 = 221,
GGML_TYPE_IQ2_S_R4 = 222,
GGML_TYPE_IQ4_XS_R4 = 223,
GGML_TYPE_IQ1_M_R4 = 229,
GGML_TYPE_BF16_R16 = 230,
GGML_TYPE_Q6_0_R4 = 233,
GGML_TYPE_IQ2_BN_R4 = 335,
@@ -516,6 +517,7 @@ extern "C" {
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_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
GGML_FTYPE_MOSTLY_IQ2_BN_R4 = 329, // except 1d tensors