tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-14 20:29:41 -04:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
* imatrix : add warning when suffix is not .gguf for GGUF imatrix

* imatrix : only warn about suffix when output format is unspecified
This commit is contained in:
compilade
2025-08-04 17:26:52 -04:00
committed by GitHub
parent 41613437ff
commit 19f68fa5a4
3 changed files with 11 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
common/arg.cpp
View File

@@ -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}));

2
common/common.h
View File

@@ -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

10
tools/imatrix/imatrix.cpp
View File

@@ -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_";