From 59d742b00fb48a3704f86c16afbb6b4ebcde8e68 Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Wed, 18 Dec 2024 13:29:25 +0100 Subject: IQ5_K_R4 (#149) * iq5_k_r4: Zen4 Much slower than the others. * iq5_k_r5: WIP * Minor * iq5_k_r4: fix AVX2 nrc_y = 1 case * iq5_k_r4: better Zen4 But TG is still slower than iq5_k * iq5_k_r4: slightly better AVX2 * iq5_k_r4: NEON --------- Co-authored-by: Iwan Kawrakow --- examples/quantize/quantize.cpp | 1 + 1 file changed, 1 insertion(+) (limited to 'examples/quantize') diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index 73485838..d505f493 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -61,6 +61,7 @@ static const std::vector QUANT_OPTIONS = { { "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", }, { "IQ5_K", LLAMA_FTYPE_MOSTLY_IQ5_K, " 5.5 bpw non-linear quantization", }, + { "IQ5_K_R4", LLAMA_FTYPE_MOSTLY_IQ5_K_R4, "IQ5_K repacked", }, { "IQ6_K", LLAMA_FTYPE_MOSTLY_IQ6_K, " 6.6 bpw non-linear quantization", }, { "Q4_K", LLAMA_FTYPE_MOSTLY_Q4_K_M, "alias for Q4_K_M", }, { "Q4_K_R4", LLAMA_FTYPE_MOSTLY_Q4_K_R4, "Q4_K_S repacked", }, -- cgit v1.2.3