happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Process target_bpw parameter

This commit is contained in:
Ed Addario 2025-08-19 10:54:02 +01:00
parent 0edbf0c176
commit e877474458
No known key found for this signature in database
GPG Key ID: E7875815A3230993
1 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
tools/quantize/quantize.cpp
View File

@ -512,6 +512,7 @@ int main(int argc, char ** argv) {
std::vector<llama_model_kv_override> kv_overrides;
std::vector<tensor_quantization> tensor_types;
std::vector<int> prune_layers;
float target_bpw = -1.0f;
for (; arg_idx < argc && strncmp(argv[arg_idx], "--", 2) == 0; arg_idx++) {
if (strcmp(argv[arg_idx], "--leave-output-tensor") == 0) {
@ -538,6 +539,10 @@ int main(int argc, char ** argv) {
if (arg_idx == argc-1 || !parse_tensor_type(argv[++arg_idx], tensor_types)) {
usage(argv[0]);
}
} else if (strcmp(argv[arg_idx], "--target-bpw") == 0) {
if (arg_idx == argc-1 || !parse_target_bpw(argv[++arg_idx], target_bpw)) {
usage(argv[0]);
}
} else if (strcmp(argv[arg_idx], "--prune-layers") == 0) {
if (arg_idx == argc-1 || !parse_layer_prune(argv[++arg_idx], prune_layers)) {
usage(argv[0]);