ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-27 09:53:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

Restore per context buffer size log

Browse Source 
Not everybody uses models split in 2000 parts, and those who do,
actually want to see the biffer sizes.
This commit is contained in:
Kawrakow
2026-02-25 13:26:37 +00:00
parent ef2ab07b5b
commit 0579a868b9
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama.cpp
View File

@@ -2209,7 +2209,7 @@ static bool llm_load_tensors(
// print memory requirements
for (ggml_backend_buffer_t buf : model.bufs) {
LLAMA_LOG_DEBUG("%s: %10s buffer size = %8.2f MiB\n", __func__, ggml_backend_buffer_name(buf), ggml_backend_buffer_get_size(buf) / 1024.0 / 1024.0);
LLAMA_LOG_INFO("%s: %10s buffer size = %8.2f MiB\n", __func__, ggml_backend_buffer_name(buf), ggml_backend_buffer_get_size(buf) / 1024.0 / 1024.0);
}
// populate tensors_by_name