Skip to content

imatrix : warn when GGUF imatrix is saved without .gguf suffix #15076

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Aug 4, 2025
Merged

imatrix : warn when GGUF imatrix is saved without .gguf suffix #15076

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
afa43e1
imatrix : add warning when suffix is not .gguf for GGUF imatrix
compilade Aug 3, 2025
342e701
imatrix : only warn about suffix when output format is unspecified
compilade Aug 3, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions common/arg.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2649,10 +2649,10 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_examples({LLAMA_EXAMPLE_IMATRIX}));
add_opt(common_arg(
{"--output-format"}, "{gguf,dat}",
string_format("output format for imatrix file (default: %s)", params.imat_dat ? "dat" : "gguf"),
string_format("output format for imatrix file (default: %s)", params.imat_dat > 0 ? "dat" : "gguf"),
[](common_params & params, const std::string & value) {
/**/ if (value == "gguf") { params.imat_dat = false; }
else if (value == "dat") { params.imat_dat = true; }
/**/ if (value == "gguf") { params.imat_dat = -1; }
else if (value == "dat") { params.imat_dat = 1; }
else { throw std::invalid_argument("invalid output format"); }
}
).set_examples({LLAMA_EXAMPLE_IMATRIX}));
Expand Down
2 changes: 1 addition & 1 deletion common/common.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -439,7 +439,7 @@ struct common_params {
int32_t n_out_freq = 10; // output the imatrix every n_out_freq iterations
int32_t n_save_freq = 0; // save the imatrix every n_save_freq iterations
int32_t i_chunk = 0; // start processing from this chunk
bool imat_dat = false; // whether the legacy imatrix.dat format should be output
int8_t imat_dat = 0; // whether the legacy imatrix.dat format should be output (gguf <= 0 < dat)

bool process_output = false; // collect data for the output tensor
bool compute_ppl = true; // whether to compute perplexity
Expand Down
10 changes: 7 additions & 3 deletions tools/imatrix/imatrix.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -506,13 +506,17 @@ 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;
int8_t use_legacy_format = m_params.imat_dat;

if (use_legacy_format) {
if (use_legacy_format > 0) {
this->save_imatrix_legacy(n_chunk);
return;
}
// else, default to GGUF imatrix
// only warn when `--output-format gguf` is not specified
if (use_legacy_format == 0 && !string_ends_with(fname, ".gguf")) {
LOG_WRN("\n%s: saving imatrix using GGUF format with a different suffix than .gguf\n", __func__);
LOG_WRN("%s: if you want the previous imatrix format, use --output-format dat\n", __func__);
}

if (n_chunk > 0) {
fname += ".at_";
Expand Down
Loading