ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-02 04:29:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

IQ3_XXS_R4 (#153)

Browse Source 
* iq3_xxs_r4: 1st shot on Zen4

PP-512: 107 t/s -> 137 t/s
TG-128(1 thread): 2.64 t/s -> 3.44 t/s

* iq4_xxs_r4: WIP

* iq4_xxs_r4: 1st shot at AVX2

Note: there is a bug in the AVX2 implementation for nrc_y = 1
for IQ quants with blocks of 32. I have fixed it for now by
using the nrc_y > 1 implementation (which works) also for nrc_y = 1.

* iq3_xxs_r4: NEON

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2024-12-20 09:12:48 +01:00
committed by GitHub
parent 8352f12275
commit 310f8b1d22
10 changed files with 351 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View File

@@ -34,6 +34,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "Q2_K_R4", LLAMA_FTYPE_MOSTLY_Q2_K_R4, "Q2_K_S repacked", },
{ "Q2_K_S", LLAMA_FTYPE_MOSTLY_Q2_K_S, " 2.16G, +9.0634 ppl @ LLaMA-v1-7B", },
{ "IQ3_XXS", LLAMA_FTYPE_MOSTLY_IQ3_XXS, " 3.06 bpw quantization", },
{ "IQ3_XXS_R4",LLAMA_FTYPE_MOSTLY_IQ3_XXS_R4,"IQ3_XXS repacked", },
{ "IQ3_S", LLAMA_FTYPE_MOSTLY_IQ3_S, " 3.44 bpw quantization", },
{ "IQ3_M", LLAMA_FTYPE_MOSTLY_IQ3_M, " 3.66 bpw quantization mix", },
{ "Q3_K", LLAMA_FTYPE_MOSTLY_Q3_K_M, "alias for Q3_K_M" },