sleepy/llama.cpp
1
0
Fork 0
Code Issues 9 Pull Requests Actions 148 Packages Projects Releases Wiki Activity

llama : update LoRA API. + fix excessive graph reserves (#19280)

Browse Source 
* Refactoring to use new llama_put_adapter_loras

* cont : alternative lora API

---------

Co-authored-by: Jake Chavis <jakechavis6@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
agent-enemy-2
2026-02-14 03:06:27 -05:00
committed by GitHub
parent eb145c0753
commit 2d8015e8a4
4 changed files with 62 additions and 88 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/common.cpp
+9 -6
View File
@@ -1223,7 +1223,7 @@ common_init_result_ptr common_init_from_params(common_params & params) {
return res;
}
int err = llama_apply_adapter_cvec(
int err = llama_set_adapter_cvec(
lctx,
cvec.data.data(),
cvec.data.size(),
@@ -1325,12 +1325,15 @@ std::string get_model_endpoint() {
}
void common_set_adapter_lora(struct llama_context * ctx, std::vector<common_adapter_lora_info> & lora) {
llama_clear_adapter_lora(ctx);
for (auto & la : lora) {
if (la.scale != 0.0f) {
llama_set_adapter_lora(ctx, la.ptr, la.scale);
}
std::vector<llama_adapter_lora *> loras;
std::vector<float> scales;
for (auto & la: lora) {
loras.push_back(la.ptr);
scales.push_back(la.scale);
}
llama_set_adapters_lora(ctx, loras.data(), loras.size(), scales.data());
}
struct llama_model_params common_model_params_to_llama(common_params & params) {