CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

imatrix : use GGUF by default

Browse Source 
Still uses the old format when the output filename ends with .dat
but this can be overridden with --output-format
This commit is contained in:
Francis Couture-Harpin
2025-07-23 21:33:53 -04:00
parent a12363bbf0
commit 53f65c354e
4 changed files with 24 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
common/arg.cpp
View File

@@ -2627,6 +2627,15 @@ 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: gguf except when output filename ends with .dat)"),
[](common_params & params, const std::string & value) {
/**/ if (value == "gguf") { params.imat_out_type = COMMON_IMATRIX_FORMAT_GGUF; }
else if (value == "dat") { params.imat_out_type = COMMON_IMATRIX_FORMAT_DAT; }
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),

7
common/common.h
View File

@@ -233,6 +233,12 @@ enum common_reasoning_format {
COMMON_REASONING_FORMAT_DEEPSEEK, // Extract thinking tag contents and return as `message.reasoning_content`, including in streaming deltas.
};
enum common_imatrix_format_type {
COMMON_IMATRIX_FORMAT_AUTO,
COMMON_IMATRIX_FORMAT_GGUF,
COMMON_IMATRIX_FORMAT_DAT, // legacy
};
struct common_params {
int32_t n_predict = -1; // new tokens to predict
int32_t n_ctx = 4096; // context size
@@ -431,6 +437,7 @@ 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
common_imatrix_format_type imat_out_type = COMMON_IMATRIX_FORMAT_AUTO; // format of the output imatrix
bool process_output = false; // collect data for the output tensor
bool compute_ppl = true; // whether to compute perplexity