ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-25 23:54:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

q6_k_r4: 1st functional AVX2 version

Browse Source
This commit is contained in:
Iwan Kawrakow
2024-12-09 20:02:57 +02:00
parent 2dce0267c9
commit 2bd2d0176a
4 changed files with 92 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View File

@@ -65,6 +65,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "Q5_K_S", LLAMA_FTYPE_MOSTLY_Q5_K_S, " 4.33G, +0.0400 ppl @ LLaMA-v1-7B", },
{ "Q5_K_M", LLAMA_FTYPE_MOSTLY_Q5_K_M, " 4.45G, +0.0122 ppl @ LLaMA-v1-7B", },
{ "Q6_K", LLAMA_FTYPE_MOSTLY_Q6_K, " 5.15G, +0.0008 ppl @ LLaMA-v1-7B", },
{ "Q6_K_R4", LLAMA_FTYPE_MOSTLY_Q6_K_R4, "Q6_K repacked", },
{ "Q8_0", LLAMA_FTYPE_MOSTLY_Q8_0, " 6.70G, +0.0004 ppl @ LLaMA-v1-7B", },
{ "Q4_0_4_4", LLAMA_FTYPE_MOSTLY_Q4_0_4_4, " 4.34G, +0.4685 ppl @ Llama-3-8B", },
{ "Q4_0_4_8", LLAMA_FTYPE_MOSTLY_Q4_0_4_8, " 4.34G, +0.4685 ppl @ Llama-3-8B", },