tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 12:35:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

cont : fix mmap flag print (#11699)

Browse Source
This commit is contained in:
Georgi Gerganov
2025-02-08 16:49:38 +02:00
parent 4d3465c5ae
commit bdcf8b6a56
2 changed files with 1 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-model.cpp
View File

@ -1275,7 +1275,7 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
const bool use_mmap_buffer = true;
LLAMA_LOG_INFO("%s: loading model tensors, this can take a while... (mmap = %s)\n", __func__, use_mmap_buffer ? "true" : "false");
LLAMA_LOG_INFO("%s: loading model tensors, this can take a while... (mmap = %s)\n", __func__, ml.use_mmap ? "true" : "false");
// build a list of buffer types for the CPU and GPU devices
pimpl->cpu_buft_list = make_cpu_buft_list(devices);

1
src/llama.cpp
View File

@ -9430,7 +9430,6 @@ static struct llama_model * llama_model_load_from_file_impl(
struct llama_model_params params) {
ggml_time_init();
unsigned cur_percentage = 0;
if (params.progress_callback == NULL) {
params.progress_callback_user_data = &cur_percentage;