CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +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

9
common/arg.cpp
View File

@@ -2647,6 +2647,15 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.n_out_freq = value;
}
).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"),
[](common_params & params, const std::string & value) {
/**/ if (value == "gguf") { params.imat_dat = false; }
else if (value == "dat") { params.imat_dat = true; }
else { throw std::invalid_argument("invalid output format"); }
}
).set_examples({LLAMA_EXAMPLE_IMATRIX}));
add_opt(common_arg(
{"--save-frequency"}, "N",
string_format("save an imatrix copy every N iterations (default: %d)", params.n_save_freq),

1
common/common.h
View File

@@ -439,6 +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
bool process_output = false; // collect data for the output tensor
bool compute_ppl = true; // whether to compute perplexity