CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-02 09:12:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into compilade/refactor-kv-cache

Browse Source
This commit is contained in:
Francis Couture-Harpin
2024-09-14 16:08:52 -04:00
parent 4bb4b22a58 822b6322de
commit 63ac36b271
144 changed files with 11344 additions and 6693 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
examples/imatrix/imatrix.cpp
View File

@@ -1,3 +1,4 @@
#include "arg.h"
#include "common.h"
#include "llama.h"
@@ -17,9 +18,7 @@
#pragma warning(disable: 4244 4267) // possible loss of data
#endif
static void print_usage(int argc, char ** argv, const gpt_params & params) {
gpt_params_print_usage(argc, argv, params);
static void print_usage(int, char ** argv) {
LOG_TEE("\nexample usage:\n");
LOG_TEE("\n %s \\\n"
" -m model.gguf -f some-text.txt [-o imatrix.dat] [--process-output] [--verbosity 1] \\\n"
@@ -579,8 +578,7 @@ int main(int argc, char ** argv) {
params.logits_all = true;
params.verbosity = 1;
if (!gpt_params_parse(argc, argv, params)) {
print_usage(argc, argv, params);
if (!gpt_params_parse(argc, argv, params, LLAMA_EXAMPLE_IMATRIX, print_usage)) {
return 1;
}
@@ -638,7 +636,8 @@ int main(int argc, char ** argv) {
g_collector.save_imatrix();
llama_print_timings(ctx);
LOG_TEE("\n");
llama_perf_context_print(ctx);
llama_free(ctx);
llama_free_model(model);