ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-24 23:24:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

iq2_kl: CUDA dequantize

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-07-10 14:22:37 +03:00
parent dfae22680b
commit d0f85cb9c2
9 changed files with 165 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View File

@@ -76,6 +76,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "IQ2_K_R4", LLAMA_FTYPE_MOSTLY_IQ2_K_R4, "IQ2_K repacked",},
{ "IQ2_KS", LLAMA_FTYPE_MOSTLY_IQ2_KS, " 2.1875 bpw non-linear quantization",},
{ "IQ2_KT", LLAMA_FTYPE_MOSTLY_IQ2_KT, " 2.125 bpw trellis quantization", },
{ "IQ2_KL", LLAMA_FTYPE_MOSTLY_IQ2_KL, " 2.69 bpw non-linear quantization", },
{ "IQ3_KS", LLAMA_FTYPE_MOSTLY_IQ3_KS, " 3.19 bpw non-linear quantization", },
{ "IQ3_K", LLAMA_FTYPE_MOSTLY_IQ3_K, " 3.44 bpw non-linear quantization", },
{ "IQ3_K_R4", LLAMA_FTYPE_MOSTLY_IQ3_K_R4, "IQ3_K repacked", },