ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-26 01:19:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

iq5_k: Basics

Browse Source 
Quantize/dequantize, CUDA dequantize
This commit is contained in:
Iwan Kawrakow
2024-07-29 12:38:46 +03:00
parent 1c2d026da6
commit f0836bdbbe
14 changed files with 650 additions and 178 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
ggml/include/ggml.h
View File

@@ -389,8 +389,9 @@ extern "C" {
GGML_TYPE_IQ1_BN = 34,
GGML_TYPE_IQ2_BN = 35,
GGML_TYPE_Q8_K64 = 36,
GGML_TYPE_IQ4_K = 37,
GGML_TYPE_IQ2_K = 38,
GGML_TYPE_IQ2_K = 37,
GGML_TYPE_IQ4_K = 38,
GGML_TYPE_IQ5_K = 39,
GGML_TYPE_COUNT,
};
@@ -437,8 +438,9 @@ extern "C" {
GGML_FTYPE_MOSTLY_Q4_0_8_8 = 27, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ1_BN = 28, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ2_BN = 29, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ4_K = 30, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ2_K = 31, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ2_K = 30, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ4_K = 31, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ5_K = 32, // except 1d tensors
};
// available tensor operations: