ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-25 07:34:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

iq1_kt: CUDA dequantize

Browse Source 
Testing with LlaMA-3.1-8B-Instruct, we get almost the same PPL
as iq2_xxs, so about 0.2 bpw fewer bits for the same quality.
This commit is contained in:
Iwan Kawrakow
2025-07-15 19:06:50 +03:00
parent 4665e5b2f3
commit 3da565c9c9
6 changed files with 58 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View File

@@ -75,6 +75,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "IQ2_K", LLAMA_FTYPE_MOSTLY_IQ2_K, " 2.375 bpw non-linear quantization",},
{ "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",},
{ "IQ1_KT", LLAMA_FTYPE_MOSTLY_IQ1_KT, " 1.75 bpw trellis 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", },