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

q2_k_r4: Zen4

Browse Source 
PP-512(LLaMA-3.1-8B) = 256 t/s
This commit is contained in:
Iwan Kawrakow
2024-12-11 16:28:56 +02:00
parent 9469af87f7
commit 93c6e295ee
10 changed files with 263 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View File

@@ -31,6 +31,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "IQ2_BN", LLAMA_FTYPE_MOSTLY_IQ2_BN, " 2.00 bpw quantization (Bitnet)", },
{ "IQ2_BN_R4",LLAMA_FTYPE_MOSTLY_IQ2_BN_R4," 2.00 bpw quantization (Bitnet)", },
{ "Q2_K", LLAMA_FTYPE_MOSTLY_Q2_K, " 2.63G, +0.6717 ppl @ LLaMA-v1-7B", },
{ "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_S", LLAMA_FTYPE_MOSTLY_IQ3_S, " 3.44 bpw quantization", },