summaryrefslogtreecommitdiff
path: root/examples/quantize/quantize.cpp
diff options
context:
space:
mode:
authorKawrakow <iwankawrakow@gmail.com>2024-12-23 14:34:23 +0100
committerGitHub <noreply@github.com>2024-12-23 14:34:23 +0100
commit167479e0272dcb5f9babc7668664fa2a75c4f2dd (patch)
treec5347677e97acaa0da4ff619c01231afeda40488 /examples/quantize/quantize.cpp
parent1a0a35dcd175a2b37fb6a347f69f31cb37eaf035 (diff)
IQ3_S_R4 (#162)
* iq3_s_r4: WIP * iq3_s_r4: Zen4 * iq3_s_r4: slightly better Zen4 * iq3_s_r4: AVX2 * iq3_s_r4: NEON * iq3_s_r4: rearrange quants * iq3_s_r4: rearranged quants - AVX2 * iq3_s_r4: rearranged quants - NEON --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'examples/quantize/quantize.cpp')
-rw-r--r--examples/quantize/quantize.cpp1
1 files changed, 1 insertions, 0 deletions
diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp
index 1599405b..5ffdbc84 100644
--- a/examples/quantize/quantize.cpp
+++ b/examples/quantize/quantize.cpp
@@ -39,6 +39,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "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_S_R4", LLAMA_FTYPE_MOSTLY_IQ3_S_R4, "IQ3_S repacked", },
{ "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" },
{ "Q3_K_R4", LLAMA_FTYPE_MOSTLY_Q3_K_R4, "Q3_K_S repacked" },