ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-25 15:44:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

iq5_ks_r4: Zen4 works

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-05-15 19:45:42 +03:00
parent 48ebde8b8b
commit 25ce0f0372
5 changed files with 164 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View File

@@ -67,6 +67,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "IQ4_XS", LLAMA_FTYPE_MOSTLY_IQ4_XS, " 4.25 bpw non-linear quantization", },
{ "IQ4_KS", LLAMA_FTYPE_MOSTLY_IQ4_KS, " 4.25 bpw non-linear quantization", },
{ "IQ4_KS_R4",LLAMA_FTYPE_MOSTLY_IQ4_KS_R4,"IQ4_KS repacked", },
{ "IQ5_KS_R4",LLAMA_FTYPE_MOSTLY_IQ5_KS_R4,"IQ5_KS repacked", },
{ "IQ4_KSS", LLAMA_FTYPE_MOSTLY_IQ4_KSS, " 4.0 bpw non-linear quantization", },
{ "IQ5_KS", LLAMA_FTYPE_MOSTLY_IQ5_KS, " 5.25 bpw non-linear quantization", },
{ "IQ2_K", LLAMA_FTYPE_MOSTLY_IQ2_K, " 2.375 bpw non-linear quantization",},