vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

common : add -dkvc arg for enabling kv cache dumps

Browse source
This commit is contained in:
Georgi Gerganov 2023-11-23 18:47:56 +02:00
parent 5df7d06c42
commit f8e9f11428
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
4 changed files with 14 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

4
common/common.cpp
View file

@ -496,6 +496,8 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) {
params.chatml = true;
} else if (arg == "--infill") {
params.infill = true;
} else if (arg == "-dkvc" || arg == "--dump-kv-cache") {
params.dump_kv_cache = true;
} else if (arg == "--multiline-input") {
params.multiline_input = true;
} else if (arg == "--simple-io") {
@ -836,6 +838,8 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
#endif // GGML_USE_CUBLAS
#endif
printf(" --verbose-prompt print prompt before generation\n");
printf(" -dkvc, --dump-kv-cache\n");
printf(" verbose print of the KV cache\n");
printf(" --simple-io use basic IO for better compatibility in subprocesses and limited consoles\n");
printf(" --lora FNAME apply LoRA adapter (implies --no-mmap)\n");
printf(" --lora-scaled FNAME S apply LoRA adapter with user defined scaling S (implies --no-mmap)\n");