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

iq2_xs: CUDA and scalar CPU works

Browse source
This commit is contained in:
Iwan Kawrakow 2024-01-09 18:19:02 +02:00
parent 9f21b82e4b
commit 9b6e38d8c0
5 changed files with 669 additions and 111 deletions
Download patch file Download diff file Expand all files Collapse all files

5
tests/test-quantize-fns.cpp
View file

@ -134,8 +134,9 @@ int main(int argc, char * argv[]) {
continue;
}
if ((ggml_type)i == GGML_TYPE_IQ2_XXS) {
printf("Skip %s due to missing quantization functionality\n", ggml_type_name((ggml_type) i));
const ggml_type ei = (ggml_type)i;
if (ei == GGML_TYPE_IQ2_XXS || ei == GGML_TYPE_IQ2_XS) {
printf("Skip %s due to missing quantization functionality\n", ggml_type_name(ei));
continue;
}