From d69344f8ea72c6fe6ec16300b939586fa9633e2e Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Tue, 17 Dec 2024 07:51:11 +0100 Subject: IQ3_K_R4 (#145) * iq3_k_r4 WIP * iq3_k_r4: Zen4 * iq3_k_r4: AVX2 * iq3_k_r4: NEON * iq3_k_r4: faster 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 5e5dd7c0..a2f83150 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -55,6 +55,7 @@ static const std::vector QUANT_OPTIONS = { { "IQ2_K", LLAMA_FTYPE_MOSTLY_IQ2_K, " 2.375 bpw non-linear quantization",}, { "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", }, { "IQ3_KL", LLAMA_FTYPE_MOSTLY_IQ3_KL, " 4 bpw non-linear quantization mix",}, { "IQ4_K", LLAMA_FTYPE_MOSTLY_IQ4_K, " 4.5 bpw non-linear quantization", }, { "IQ4_K_R4", LLAMA_FTYPE_MOSTLY_IQ4_K_R4, "IQ4_K repacked", }, -- cgit v1.2.3