ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-06 20:10:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

iq1_m_r4: Zen4 gemm

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-02-05 19:45:45 +02:00
parent 212e8d192e
commit b0ba33bec0
4 changed files with 132 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/quantize/quantize.cpp
View File

@@ -30,6 +30,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "IQ2_M_R4", LLAMA_FTYPE_MOSTLY_IQ2_M_R4, " 2.7 bpw quantization", },
{ "IQ1_S", LLAMA_FTYPE_MOSTLY_IQ1_S, " 1.56 bpw quantization", },
{ "IQ1_S_R4", LLAMA_FTYPE_MOSTLY_IQ1_S_R4, " 1.5 bpw quantization", },
{ "IQ1_M_R4", LLAMA_FTYPE_MOSTLY_IQ1_M_R4, " 1.75 bpw quantization", },
{ "IQ1_M", LLAMA_FTYPE_MOSTLY_IQ1_M, " 1.75 bpw quantization", },
{ "IQ1_BN", LLAMA_FTYPE_MOSTLY_IQ1_BN, " 1.62 bpw quantization (Bitnet)", },
{ "IQ2_BN", LLAMA_FTYPE_MOSTLY_IQ2_BN, " 2.00 bpw quantization (Bitnet)", },
@@ -512,6 +513,7 @@ int main(int argc, char ** argv) {
params.ftype == LLAMA_FTYPE_MOSTLY_Q2_K_S || params.ftype == LLAMA_FTYPE_MOSTLY_IQ2_XS_R4 ||
params.ftype == LLAMA_FTYPE_MOSTLY_IQ1_S ||
params.ftype == LLAMA_FTYPE_MOSTLY_IQ1_S_R4 ||
params.ftype == LLAMA_FTYPE_MOSTLY_IQ1_M_R4 ||
params.ftype == LLAMA_FTYPE_MOSTLY_IQ1_M)) {
fprintf(stderr, "\n==========================================================================================================\n");
fprintf(stderr, "Please do not use IQ1_S, IQ1_M, IQ2_S, IQ2_XXS, IQ2_XS or Q2_K_S quantization without an importance matrix\n");