happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

llama-model-loader: print warning when using overrides with mmap (#20978) 

* llama-model-loader: use pinned memory for tensor overrides

* change to warning
This commit is contained in:
Aman Gupta 2026-03-30 17:40:17 +08:00 committed by GitHub
parent e2eb39e81c
commit 278521c33a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/llama-model-loader.cpp
View File

@ -1158,6 +1158,12 @@ struct ggml_tensor * llama_model_loader::create_tensor(
if (overrides->buft == ggml_backend_cpu_buffer_type()) {
// when overriding to a CPU buffer, consider the extra buffer types
buft = select_weight_buft(hparams, t_meta, op, buft_list_cpu);
if (use_mmap) {
static std::once_flag once;
std::call_once(once, [] {
LLAMA_LOG_WARN("llama_model_loader: tensor overrides to CPU are used with mmap enabled - consider using --no-mmap for better performance\n");
});
}
} else {
buft = overrides->buft;
}