sleepy/llama.cpp
1
0
Fork 0
Code Issues 11 Pull Requests Actions 109 Packages Projects Releases Wiki Activity

lora: count lora nodes in graph_max_nodes (#18469)

Browse Source 
* lora: count lora nodes in graph_max_nodes

* 3 nodes per weight

* 4 nodes

* keep track n_lora_nodes from llama_model

* fix assert

* rm redundant header

* common: load adapters before context creation

* use 6 nodes
This commit is contained in:
Xuan-Son Nguyen
2025-12-30 15:53:12 +01:00
committed by GitHub
parent c32fa21db8
commit cd78e57c3a
6 changed files with 46 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/common.cpp
+19 -18
View File
@@ -1109,6 +1109,25 @@ 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)
for (auto & la : params.lora_adapters) {
llama_adapter_lora_ptr lora;
lora.reset(llama_adapter_lora_init(model, la.path.c_str()));
if (lora == nullptr) {
LOG_ERR("%s: failed to load lora adapter '%s'\n", __func__, la.path.c_str());
pimpl->model.reset(model);
return;
}
char buf[1024];
la.ptr = lora.get();
llama_adapter_meta_val_str(la.ptr, "adapter.lora.task_name", buf, sizeof(buf));
la.task_name = buf;
llama_adapter_meta_val_str(la.ptr, "adapter.lora.prompt_prefix", buf, sizeof(buf));
la.prompt_prefix = buf;
pimpl->lora.emplace_back(std::move(lora)); // copy to list of loaded adapters
}
// updates params.sampling
// TODO: fix naming
common_init_sampler_from_model(model, params.sampling);
@@ -1245,24 +1264,6 @@ common_init_result_ptr common_init_from_params(common_params & params) {
}
}
// 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()));
if (lora == nullptr) {
LOG_ERR("%s: failed to apply lora adapter '%s'\n", __func__, la.path.c_str());
return res;
}
char buf[1024];
la.ptr = lora.get();
llama_adapter_meta_val_str(la.ptr, "adapter.lora.task_name", buf, sizeof(buf));
la.task_name = buf;
llama_adapter_meta_val_str(la.ptr, "adapter.lora.prompt_prefix", buf, sizeof(buf));
la.prompt_prefix = buf;
res->lora().emplace_back(std::move(lora)); // copy to list of loaded adapters
}
if (!params.lora_init_without_apply) {
common_set_adapter_lora(lctx, params.lora_adapters);
}