From 7a32fcb3b29f4db8aed8a85dc58eb958fb118153 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Tue, 25 Apr 2023 23:40:51 +0300 Subject: ggml : add Q8_0 quantization format (rename the old one to Q8_1) (ARM NEON) (#1179) * ggml : add Q8_0 quantization format (rename the old one to Q8_1) * tests : fix test-quantize-fns * ggml : finalize Q8_0 implementation * ggml : use q4_0_q8_0 and q4_2_q8_0 * ggml : fix Q8_0 dot product bug (ARM) * ggml : Q8_0 unroll x2 * ggml : fix bug - using wrong block type * ggml : extend quantize_fns_t with "vec_dot_type" * ggml : fix Q8_0 to use 255 values out of 256 * ggml : fix assert using wrong QK4_2 instead of QK4_3 --- llama.h | 1 + 1 file changed, 1 insertion(+) (limited to 'llama.h') diff --git a/llama.h b/llama.h index e9e3abea..ab41798d 100644 --- a/llama.h +++ b/llama.h @@ -74,6 +74,7 @@ extern "C" { LLAMA_FTYPE_MOSTLY_Q4_1_SOME_F16 = 4, // tok_embeddings.weight and output.weight are F16 LLAMA_FTYPE_MOSTLY_Q4_2 = 5, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q4_3 = 6, // except 1d tensors + LLAMA_FTYPE_MOSTLY_Q8_0 = 7, // except 1d tensors }; LLAMA_API struct llama_context_params llama_context_default_params(); -- cgit v1.2.3