From c1f885067c61191a07a1aedf684168dda62f3f71 Mon Sep 17 00:00:00 2001 From: Stephan Walter Date: Tue, 28 Mar 2023 15:56:03 +0000 Subject: ggml : introduce structs for the q4 data blocks (#356) * Introduce structs for the q4 data blocks * ggml : rename quant struct variables + fix ARM_NEON --------- Co-authored-by: Georgi Gerganov --- examples/quantize/quantize.cpp | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'examples/quantize/quantize.cpp') diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index f0230f5d..3888ff58 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -4,8 +4,6 @@ #include #include -const int QK = 32; - // usage: // ./llama-quantize models/llama/ggml-model.bin models/llama/ggml-model-quant.bin type // @@ -39,7 +37,7 @@ int main(int argc, char ** argv) { { const int64_t t_start_us = ggml_time_us(); - if (llama_model_quantize(fname_inp.c_str(), fname_out.c_str(), itype, QK)) { + if (llama_model_quantize(fname_inp.c_str(), fname_out.c_str(), itype)) { fprintf(stderr, "%s: failed to quantize model from '%s'\n", __func__, fname_inp.c_str()); return 1; } -- cgit v1.2.3