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

ggml : add I32 <-> F32 conversion

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-02-23 14:14:49 +02:00
parent fc775366f1
commit 8772658b11
No known key found for this signature in database
GPG key ID: BF970631944C16B7
4 changed files with 53 additions and 36 deletions
Download patch file Download diff file Expand all files Collapse all files

6
tests/test-quantize-fns.cpp
View file

@ -143,10 +143,10 @@ int main(int argc, char * argv[]) {
continue;
}
printf("Testing %s\n", ggml_type_name((ggml_type) i));
ggml_quantize_init(ei);
if (qfns.from_float && qfns.to_float && qfns.vec_dot) {
printf("Testing %s\n", ggml_type_name((ggml_type) i));
ggml_quantize_init(ei);
if (qfns.from_float && qfns.to_float) {
const float total_error = total_quantization_error(qfns, test_size, test_data.data());
const float max_quantization_error =
type == GGML_TYPE_Q2_K ? MAX_QUANTIZATION_TOTAL_ERROR_2BITS :