ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-13 15:30:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Check for NaNs while loading the model. (#727)

Browse Source 
* Check for NaNs while loading the model.

* Also tell which experts have NaNs.

* Add command line option to validate quants

* Add checks for more quantization types

* Add checks for more quantizagtion types

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-08-27 19:00:17 +03:00
committed by GitHub
parent ca5b6ab9b1
commit e760b4dc41
6 changed files with 199 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
include/llama.h
View File

@@ -377,7 +377,8 @@ extern "C" {
bool use_mlock; // force system to keep model in RAM
bool check_tensors; // validate model tensor data
bool repack_tensors;// repack if available
bool use_thp; // uase transparent huge pages (linux only)
bool use_thp; // use transparent huge pages (linux only)
bool validate_quants; // if true, check for NaNs while loading the model
};
// NOTE: changing the default values of parameters marked as [EXPERIMENTAL] may cause crashes or incorrect results in certain configurations