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

lora: load to devide buft

Browse source
This commit is contained in:
ngxson 2024-07-06 02:12:53 +02:00
parent 213701b51a
commit 67c5e14d06
3 changed files with 172 additions and 274 deletions
Download patch file Download diff file Expand all files Collapse all files

10
common/common.cpp
View file

@ -2063,14 +2063,8 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
for (unsigned int i = 0; i < params.lora_adapter.size(); ++i) {
const std::string & lora_adapter = std::get<0>(params.lora_adapter[i]);
float lora_scale = std::get<1>(params.lora_adapter[i]);
int err = llama_model_apply_lora_from_file(model,
lora_adapter.c_str(),
lora_scale,
((i > 0) || params.lora_base.empty())
? NULL
: params.lora_base.c_str(),
params.n_threads);
if (err != 0) {
auto adapter = llama_lora_adapter_init(lctx, lora_adapter.c_str());
if (adapter == nullptr) {
fprintf(stderr, "%s: error: failed to apply lora adapter\n", __func__);
llama_free(lctx);
llama_free_model(model);