ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-26 08:04:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

iq3_xxs_r4: 1st shot on Zen4

Browse Source 
PP-512: 107 t/s -> 137 t/s
TG-128(1 thread): 2.64 t/s -> 3.44 t/s
This commit is contained in:
Iwan Kawrakow
2024-12-19 12:19:34 +02:00
parent dfa12b7f91
commit ef0eeacadb
10 changed files with 252 additions and 5 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" },