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

llama : update llama_model API names (#11063)

Browse source 
* llama : deprecate llama_free_model, add llama_model_free

ggml-ci

* llama : change `llama_load_model_from_file` -> `llama_model_load_from_file`

ggml-ci
This commit is contained in:
Georgi Gerganov 2025-01-06 10:55:18 +02:00 • committed by GitHub
parent 3e6e7a6bc2
commit 47182dd03f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
23 changed files with 76 additions and 59 deletions
Download patch file Download diff file Expand all files Collapse all files

8
examples/quantize-stats/quantize-stats.cpp
View file

@ -309,7 +309,7 @@ int main(int argc, char ** argv) {
auto mparams = llama_model_default_params();
mparams.use_mlock = false;
model = llama_load_model_from_file(params.model.c_str(), mparams);
model = llama_model_load_from_file(params.model.c_str(), mparams);
if (model == NULL) {
fprintf(stderr, "%s: error: failed to load model '%s'\n", __func__, params.model.c_str());
@ -323,7 +323,7 @@ int main(int argc, char ** argv) {
if (ctx == NULL) {
fprintf(stderr, "%s: error: failed to create context with model '%s'\n", __func__, params.model.c_str());
llama_free_model(model);
llama_model_free(model);
return 1;
}
}
@ -347,7 +347,7 @@ int main(int argc, char ** argv) {
fprintf(stderr, "%s: error: Quantization should be tested with a float model, "
"this model contains already quantized layers (%s is type %d)\n", __func__, kv_tensor.first.c_str(), kv_tensor.second->type);
llama_free(ctx);
llama_free_model(model);
llama_model_free(model);
return 1;
}
included_layers++;
@ -409,7 +409,7 @@ int main(int argc, char ** argv) {
llama_free(ctx);
llama_free_model(model);
llama_model_free(model);
// report timing
{
const int64_t t_main_end_us = ggml_time_us();