From dfa12b7f91b9d71bc11f5042151bde949da04d61 Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Wed, 18 Dec 2024 19:58:21 +0100 Subject: IQ4_KS_R4 (#150) * iq4_ks_r4: Zen4 * iq4_ks_r4: AVX2 * iq4_ks_r4: WIP * iq4_ks_r4: slightly better Zen4 * iq4_ks_r4: slightly better Zen4 * iq4_ks_r4: NEON * Minor --------- Co-authored-by: Iwan Kawrakow --- examples/quantize/quantize.cpp | 1 + 1 file changed, 1 insertion(+) (limited to 'examples') diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index d505f493..cefe2735 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -51,6 +51,7 @@ static const std::vector QUANT_OPTIONS = { { "Q8_0_R4", LLAMA_FTYPE_MOSTLY_Q8_0_R4, " 8.50 bpw quantization", }, { "IQ4_XS", LLAMA_FTYPE_MOSTLY_IQ4_XS, " 4.25 bpw non-linear quantization", }, { "IQ4_KS", LLAMA_FTYPE_MOSTLY_IQ4_KS, " 4.25 bpw non-linear quantization", }, + { "IQ4_KS_R4",LLAMA_FTYPE_MOSTLY_IQ4_KS_R4,"IQ4_KS repacked", }, { "IQ4_KSS", LLAMA_FTYPE_MOSTLY_IQ4_KSS, " 4.0 bpw non-linear quantization", }, { "IQ2_K", LLAMA_FTYPE_MOSTLY_IQ2_K, " 2.375 bpw non-linear quantization",}, { "IQ2_K_R4", LLAMA_FTYPE_MOSTLY_IQ2_K_R4, "IQ2_K repacked",}, -- cgit v1.2.3