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

IQ4_K_R4 (#138)

Browse Source 
* iq4_k_r4: WIP

* iq4_k_r4: Zen4 and hopefully AVX2

On Zen4 we get PP-512(LLaMA-3.1-8B) = 232.6 t/s, up from 182.2 t/s
for iq4_k. Applying the extra shift costs a ~6 performance penalty.

* iq4_k_r4: AVX2

PP-512 = 227.60 t/s. The shifts are really costly.

* iq4_k_r4: NEON

We get PP-512(LLaMA-3.1-8B) = 108 t/s, up from 58.2 t/s for iq4_k.

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2024-12-12 16:04:20 +01:00
committed by GitHub
parent 66ade83e56
commit ce97b0325e
10 changed files with 443 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View File

@@ -57,6 +57,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "IQ3_K", LLAMA_FTYPE_MOSTLY_IQ3_K, " 3.44 bpw non-linear quantization", },
{ "IQ3_KL", LLAMA_FTYPE_MOSTLY_IQ3_KL, " 4 bpw non-linear quantization mix",},
{ "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", },
{ "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", },