From 3ec193b4856df8e5827b83a8c7686e8498c5e5b8 Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Mon, 9 Dec 2024 16:59:18 +0100 Subject: Q4_K_R4 (#129) * Something is still wrong * Simply don't see what is wrong * q4_k_r4: finally works on Zen4 I had forgotten to prevent token_embd.weight being quantized with q4_k_r4! * q4_k_r4: AVX2 We get PP-512(LLaMA-3.1-8B) = 267 t/s on a Ryzen-5975WX. This is ~30% better than Q4_K_S. * q4_k_r4: NEON We get PP-512(LLaMA-3.1-8B) = 110 t/s. Not quite as good as q4_0_r4, but still a massive improvement compared to he 69 t/s for q4_K. * q4_k_r4: slightly better AVX2 PP-512 goes from 267 t/s to 282 t/s on Ryzen-5975WX * Minor * Minor --------- 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 24e5a61b..731ea3ff 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -58,6 +58,7 @@ static const std::vector QUANT_OPTIONS = { { "IQ5_K", LLAMA_FTYPE_MOSTLY_IQ5_K, " 5.5 bpw non-linear quantization", }, { "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", }, { "Q4_K_S", LLAMA_FTYPE_MOSTLY_Q4_K_S, " 3.59G, +0.0992 ppl @ LLaMA-v1-7B", }, { "Q4_K_M", LLAMA_FTYPE_MOSTLY_Q4_K_M, " 3.80G, +0.0532 ppl @ LLaMA-v1-7B", }, { "Q5_K", LLAMA_FTYPE_MOSTLY_Q5_K_M, "alias for Q5_K_M", }, -- cgit v1.2.3