ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-01-26 17:20:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Adding IQ1_KT - 1.75 bpw SOTA quants (#616)

Browse Source 
* iq1_kt: basics

* iq1_kt: CUDA dequantize

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.

* iq1_kt: CUDA MMQ

* iq1_kt: CUDA MMVQ

* iq1_kt: AVX2 GEMM/GEMV

* iq1_kt: convert/repack to q8_0_r8 (AVX2)

* iq1_kt: slightly faster GEMV

18.6 t/s -> 19.4 t/s

* iq1_kt: NEON GEMM/GEMV

Pathetic as usual

* iq1_kt: slightly faster NEON - still pathetic

* iq1_kt: tiny bit better GEMV on NEON

* iq1_kt: convert/repack to q8_0_r8 (NEON)

* iq1_kt: very slightly faster convert/repack to q8_0_r8 on NEON

* Adding frgotten file

* iq1_kt: add to constants.py

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-07-20 10:05:23 +02:00
committed by GitHub
parent d0bc1f8296
commit e1164e1fd8
21 changed files with 930 additions and 6 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", },