mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-04-16 03:26:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

model : print tensor size during load (#12711)

Browse Source 
* model : print tensor size during load

* cont : fix units MB -> MiB

Co-authored-by: Diego Devesa <slarengh@gmail.com>

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
This commit is contained in:
Georgi Gerganov 2025-04-02 16:38:54 +03:00 committed by GitHub
parent e0e912f49b
commit 833e2b7409
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/llama-model-loader.cpp
View File

@ -603,7 +603,9 @@ llama_model_loader::llama_model_loader(
if (trace > 0) {
const uint16_t sid = w.idx;
LLAMA_LOG_INFO("%s: - tensor split %2d: %32s %-8s [ %s ]\n", __func__, sid, ggml_get_name(tensor), ggml_type_name(type), llama_format_tensor_shape(tensor).c_str());
LLAMA_LOG_INFO("%s: - tensor split %2d: %32s %-8s [ %s ] %8.2f MiB\n", __func__,
sid, ggml_get_name(tensor), ggml_type_name(type), llama_format_tensor_shape(tensor).c_str(),
ggml_nbytes(tensor)/1024.0f/1024.0f);
}
}