From 49662cbed3e95f5976c070b85b9fd53fd577038d Mon Sep 17 00:00:00 2001 From: Kawrakow <48489457+ikawrakow@users.noreply.github.com> Date: Thu, 11 Jan 2024 20:39:39 +0100 Subject: ggml : SOTA 2-bit quants (add IQ2_XS) (#4856) * iq2_xs: basics * iq2_xs: this should have been in the basics * iq2_xs: CUDA and scalar CPU works * iq2_xs: WIP Metal * iq2_xs: Metal now works * iq2_xs: working, but dog slow, ARM_NEON dot product * iq2_xs: better ARM_NEON dot product We are now at 19.5 t/s for TG-128 and 61 t/s for PP-512 when running on the CPU. * iq2_xs: AVX2 dot product - 19.5 t/s * iq2_xs: faster AVX2 dit product 21.4 t/s for TG-128, 59.2 t/s for PP-512. The latter is 2x compared to the previous version. * iq2_xs: had forgotten to delete iq2-data.h * Add llama enum for IQ2_XS --------- Co-authored-by: Iwan Kawrakow --- llama.h | 1 + 1 file changed, 1 insertion(+) (limited to 'llama.h') diff --git a/llama.h b/llama.h index c11075bb..6fde113f 100644 --- a/llama.h +++ b/llama.h @@ -104,6 +104,7 @@ extern "C" { LLAMA_FTYPE_MOSTLY_Q5_K_M = 17, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q6_K = 18, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ2_XXS = 19, // except 1d tensors + LLAMA_FTYPE_MOSTLY_IQ2_XS = 20, // except 1d tensors LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file }; -- cgit v1.2.3