From 4ade4c568c331acad22537f7b9519c740c7a06d0 Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Tue, 17 Dec 2024 10:18:33 +0100 Subject: IQ2_K_R4 (#146) * iq2_k_r4: Zen4 * iq2_k_r4: NEON * iq2_k_r4: better matrix x vector multiplication on NEON --------- 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 a2f83150..73485838 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -53,6 +53,7 @@ static const std::vector QUANT_OPTIONS = { { "IQ4_KS", LLAMA_FTYPE_MOSTLY_IQ4_KS, " 4.25 bpw non-linear quantization", }, { "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",}, { "IQ2_KS", LLAMA_FTYPE_MOSTLY_IQ2_KS, " 2.1875 bpw non-linear quantization",}, { "IQ3_K", LLAMA_FTYPE_MOSTLY_IQ3_K, " 3.44 bpw non-linear quantization", }, { "IQ3_K_R4", LLAMA_FTYPE_MOSTLY_IQ3_K_R4, "IQ3_K repacked", }, -- cgit v1.2.3