Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-20 01:31:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	examples/server/README.md
#	src/llama-model.cpp
This commit is contained in:
Concedo
2025-02-08 22:57:18 +08:00
parent a83f2d5fce bdcf8b6a56
commit 3fa4843850
7 changed files with 61 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+1 -2
View File
@@ -1280,8 +1280,7 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
bool use_mmap_buffer = true;
LLAMA_LOG_INFO("%s: loading model tensors, this can take a while...", __func__);
// 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);
src/llama.cpp
-1
View File
@@ -9471,7 +9471,6 @@ 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;