thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

llama : re-enable manual LoRA adapter free (#19983)

Browse source 
* Re-enable manual LoRA adapter free

* Remove stale "all adapters must be loaded before context creation" stale comments
This commit is contained in:
Pop Flamingo 2026-03-18 11:03:26 +01:00 • committed by GitHub
parent f4049ad735
commit 312cf03328
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 19 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

2
common/common.cpp
View file

@ -1067,7 +1067,7 @@ common_init_result::common_init_result(common_params & params) :
const llama_vocab * vocab = llama_model_get_vocab(model);
// load and optionally apply lora adapters (must be loaded before context creation)
// load and optionally apply lora adapters
for (auto & la : params.lora_adapters) {
llama_adapter_lora_ptr lora;
lora.reset(llama_adapter_lora_init(model, la.path.c_str()));