From ccec00939a30aa7762a232ac4dcadba985ef9ee4 Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Tue, 3 Dec 2024 06:15:29 +0100 Subject: Q8_0_R4 (#120) * Adding q8_0_r4 We get PP-512(LLaMA-3.1-8B) = 268 t/s on a Ryzen-7950X compared to 175.6 t/s for Q8_0. * q8_0_r4: NEON We get PP-512(LLaMA-3.1-8B) = 112.6 t/s on M2-Max. * q8_0_r4: Zen4 matrix-vector specialization --------- 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 9e0dc3cf..6cac41a2 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -42,6 +42,7 @@ static const std::vector QUANT_OPTIONS = { { "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", }, + { "Q8_0_R4", LLAMA_FTYPE_MOSTLY_Q8_0_R4, " 8.50 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