CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

imatrix : use GGUF by default (#14842)

Browse Source 
* imatrix : use GGUF by default

* imatrix : use GGUF regardless of the output filename

The legacy format can only be produced with --output-format dat
This commit is contained in:
compilade
2025-08-03 16:00:05 -04:00
committed by GitHub
parent 0a2f5496be
commit d31192b4ee
4 changed files with 23 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tools/imatrix/imatrix.cpp
View File

@@ -26,7 +26,7 @@
static void print_usage(int, char ** argv) {
LOG("\nexample usage:\n");
LOG("\n %s \\\n"
" -m model.gguf -f some-text.txt [-o imatrix.gguf] [--no-ppl] \\\n"
" -m model.gguf -f some-text.txt [-o imatrix.gguf] [--output-format {gguf,dat}] [--no-ppl] \\\n"
" [--process-output] [--chunk 123] [--save-frequency 0] [--output-frequency 10] \\\n"
" [--in-file imatrix-prev-0.gguf --in-file imatrix-prev-1.gguf ...] [--parse-special] \\\n"
" [--show-statistics] [...]\n" , argv[0]);
@@ -506,13 +506,13 @@ void IMatrixCollector::save_imatrix_legacy(int32_t ncall) const {
void IMatrixCollector::save_imatrix(int32_t n_chunk) const {
auto fname = m_params.out_file;
bool use_legacy_format = m_params.imat_dat;
// TODO: use the new format in more cases
if (!string_ends_with(fname, ".gguf")) {
LOG_WRN("\n%s: saving to legacy imatrix format because output suffix is not .gguf\n", __func__);
if (use_legacy_format) {
this->save_imatrix_legacy(n_chunk);
return;
}
// else, default to GGUF imatrix
if (n_chunk > 0) {
fname += ".at_";