From 239a344f9935cb614c6208000edb0815214286a1 Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Mon, 2 Dec 2024 17:01:48 +0100 Subject: Q4_0_R4 (#119) * Adding iq4_0_r4 - q4_0 repacked We get PP-512(LLaMA-3.1-8B) = 278 t/s on a Ryzen-7950X CPU, so ~5-6% faster than iq4_nl_x4. * q4_0_r4: NEON Here we get 115.8 t/s, so also ~5% better than iq4_nl_x4. --------- 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 333fae36..9e0dc3cf 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -41,6 +41,7 @@ static const std::vector QUANT_OPTIONS = { { "Q3_K_L", LLAMA_FTYPE_MOSTLY_Q3_K_L, " 3.35G, +0.1764 ppl @ LLaMA-v1-7B", }, { "IQ4_NL", LLAMA_FTYPE_MOSTLY_IQ4_NL, " 4.50 bpw non-linear quantization", }, { "IQ4_NL_X4",LLAMA_FTYPE_MOSTLY_IQ4_NL_X4," 4.50 bpw non-linear quantization", }, + { "Q4_0_R4", LLAMA_FTYPE_MOSTLY_Q4_0_R4, " 4.50 bpw non-linear 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_KSS", LLAMA_FTYPE_MOSTLY_IQ4_KSS, " 4.0 bpw non-linear quantization", }, -- cgit v1.2.3