vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml : introduce structs for the q4 data blocks (#356)

Browse source 
* Introduce structs for the q4 data blocks

* ggml : rename quant struct variables + fix ARM_NEON

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Stephan Walter 2023-03-28 15:56:03 +00:00 • committed by GitHub
parent e0670260fb
commit c1f885067c
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 150 additions and 235 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/quantize/quantize.cpp
View file

@ -4,8 +4,6 @@
#include <cstdio>
#include <string>
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;
}