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

iq2_k: Basics

Browse Source 
Quantize/dequantize, CUDA deqantize, AVX512 iqk_mul_mat.
This commit is contained in:
Kawrakow
2024-07-28 19:43:18 +03:00
committed by Kawrakow
parent 007d2a56b3
commit 3f7dad3000
15 changed files with 451 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View File

@@ -40,6 +40,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "Q3_K_L", LLAMA_FTYPE_MOSTLY_Q3_K_L, " 3.35G, +0.1764 ppl @ LLaMA-v1-7B", },
{ "IQ4_NL", LLAMA_FTYPE_MOSTLY_IQ4_NL, " 4.50 bpw non-linear quantization", },
{ "IQ4_XS", LLAMA_FTYPE_MOSTLY_IQ4_XS, " 4.25 bpw non-linear quantization", },
{ "IQ2_K", LLAMA_FTYPE_MOSTLY_IQ2_K, " 2.375 bpw non-linear quantization",},
{ "IQ4_K", LLAMA_FTYPE_MOSTLY_IQ4_K, " 4.5 bpw non-linear quantization", },
{ "Q4_K", LLAMA_FTYPE_MOSTLY_Q4_K_M, "alias for Q4_K_M", },
{ "Q4_K_S", LLAMA_FTYPE_MOSTLY_Q4_K_S, " 3.59G, +0.0992 ppl @ LLaMA-v1-7B", },