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

IQ5_K_R4 (#149)

Browse Source 
* iq5_k_r4: Zen4

Much slower than the others.

* iq5_k_r5: WIP

* Minor

* iq5_k_r4: fix AVX2 nrc_y = 1 case

* iq5_k_r4: better Zen4

But TG is still slower than iq5_k

* iq5_k_r4: slightly better AVX2

* iq5_k_r4: NEON

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2024-12-18 13:29:25 +01:00
committed by GitHub
parent 2247afa967
commit c208fec2f2
10 changed files with 532 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View File

@@ -61,6 +61,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "IQ4_K", LLAMA_FTYPE_MOSTLY_IQ4_K, " 4.5 bpw non-linear quantization", },
{ "IQ4_K_R4", LLAMA_FTYPE_MOSTLY_IQ4_K_R4, "IQ4_K repacked", },
{ "IQ5_K", LLAMA_FTYPE_MOSTLY_IQ5_K, " 5.5 bpw non-linear quantization", },
{ "IQ5_K_R4", LLAMA_FTYPE_MOSTLY_IQ5_K_R4, "IQ5_K repacked", },
{ "IQ6_K", LLAMA_FTYPE_MOSTLY_IQ6_K, " 6.6 bpw non-linear quantization", },
{ "Q4_K", LLAMA_FTYPE_MOSTLY_Q4_K_M, "alias for Q4_K_M", },
{ "Q4_K_R4", LLAMA_FTYPE_MOSTLY_Q4_K_R4, "Q4_K_S repacked", },