thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

tool/ex/tests: consistently free ctx, then model (#18168)

Browse source
This commit is contained in:
Johannes Gäßler 2025-12-22 11:00:37 +01:00 • committed by GitHub
parent e1f15b454f
commit 147a521636
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 48 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

2
common/common.cpp
View file

@ -1078,6 +1078,8 @@ struct common_init_result::impl {
impl() = default;
~impl() = default;
// note: the order in which model, context, etc. are declared matters because their destructors will be called bottom-to-top
llama_model_ptr model;
llama_context_ptr context;