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

metal : fix build(#17799)

Browse source 
* metal : fix build

* tests : fix context destruction
This commit is contained in:
Georgi Gerganov 2025-12-06 09:33:59 +02:00 • committed by GitHub
parent 67788f6846
commit 8ce774a102
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 23 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

6
examples/save-load-state/save-load-state.cpp
View file

@ -241,6 +241,12 @@ int main(int argc, char ** argv) {
llama_batch_free(batch);
// this one is managed by common_init_result
//llama_free(ctx);
llama_free(ctx2);
llama_free(ctx3);
if (result0 != result2) {
fprintf(stderr, "\n%s : error : the seq restore generation is different\n", __func__);
return 1;